allenai/Molmo2-4B
hf allenai/Molmo2-4B 2 sources, 2 claims · Watch
What each source says
| Property | Source | Said | Means here | ||||
|---|---|---|---|---|---|---|---|
| Author author not compared | GGUF quantisations | mu2solutionsreceipt
What the source handed over{
"_id": "6abaa26c4f2c2ba1836b05f0",
"author": "mu2solutions",
"cardData": {
"base_model": "allenai/Molmo2-4B",
"license": "apache-2.0",
"pipeline_tag": "image-text-to-text",
"tags": [
"gguf",
"llama.cpp",
"allenai",
"molmo",
"vision",
"image-text-to-text"
]
},
"createdAt": "2026-09-28T17:22:52.000Z",
"downloads": 117,
"gated": false,
"id": "mu2solutions/Molmo2-4B-GGUF",
"lastModified": "2026-09-28T17:24:11.000Z",
"likes": 0,
"modelId": "mu2solutions/Molmo2-4B-GGUF",
"pipeline_tag": "image-text-to-text",
"private": false,
"sha": "d3c8673e31ef68266e7396c45d13b404bf499389",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "Molmo2-4B-mmproj-F16.gguf"
},
{
"rfilename": "Molmo2-4B-text-Q4_K_M.gguf"
},
{
"rfilename": "README.md"
},
{
"rfilename": "SHA256SUMS.txt"
}
],
"tags": [
"gguf",
"llama.cpp",
"allenai",
"molmo",
"vision",
"image-text-to-text",
"base_model:allenai/Molmo2-4B",
"base_model:quantized:allenai/Molmo2-4B",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
]
} | — | ||||
| Author author not compared | Hugging Face models | allenaireceipt
What the source handed over{
"_asked": "allenai/Molmo2-4B",
"_id": "693f4077d9c3e9aae0b943b1",
"author": "allenai",
"cardData": {
"base_model": [
"google/siglip-so400m-patch14-384",
"Qwen/Qwen3-4B-Instruct-2507"
],
"datasets": [
"allenai/Molmo2-Cap",
"allenai/Molmo2-VideoCapQA",
"allenai/Molmo2-VideoSubtitleQA",
"allenai/Molmo2-AskModelAnything",
"allenai/Molmo2-VideoPoint",
"allenai/Molmo2-VideoTrack",
"allenai/Molmo2-MultiImageQA",
"allenai/Molmo2-SynMultiImageQA",
"allenai/Molmo2-MultiImagePoint"
],
"language": [
"en"
],
"library_name": "transformers",
"license": "apache-2.0",
"pipeline_tag": "image-text-to-text",
"tags": [
"multimodal",
"olmo",
"molmo",
"molmo2"
]
},
"config": {
"architectures": [
"Molmo2ForConditionalGeneration"
],
"auto_map": {
"AutoConfig": "configuration_molmo2.Molmo2Config",
"AutoModelForImageTextToText": "modeling_molmo2.Molmo2ForConditionalGeneration"
},
"chat_template_jinja": "{% set DEMO_STYLES = ['point_count','pointing','cosyn_point','user_qa','long_caption','short_caption','video_long_caption','video_short_caption','video_point_track_per_frame','video_point_track_start_end','video_point_track_all_frames','video_single_point_track_start_end','video_transcript','video_clip_caption_start_end','video_clip_caption_start_end_in_seconds','video_clip_transcript_start_end','video_clip_transcript_start_end_in_seconds','video_frame_caption_timestamp','video_frame_caption_timestamp_in_seconds','correction_qa','text_sft','video_point','video_point_count','video_count','video_count_point','multi_image_pointing','multi_image_counting','multi_image_point_then_count','multi_image_count_then_point','demo','a_okvqa_mc','ai2_diagram_no_letter','ai2_diagram','science_qa','multi_image_mc','multi_image_mc_exp','mantis_instruct_mc','video_multiple_choice','video_multiple_choice_count_without_pointing','video_multiple_choice_multiple_correct','video_multiple_choice_w_subtitle'] %}{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% set has_subtitle = messages and messages[0]['role'].lower() == 'subtitle' %}{% for message in messages %}{% if message['content'] is not string %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% elif content['type'] == 'video' or 'video' in content or 'video_url' in content %}{% set video_count.value = video_count.value + 1 %}{% endif %}{% endfor %}{% endif %}{% endfor %}{% if image_count.value == 1 %}{{ '<|image|>' }}{% elif image_count.value > 1 %}{% for i in range(image_count.value) %}{{ 'Image ' ~ (i + 1) ~ '<|image|>' }}{% endfor %}{% endif %}{% for _ in range(video_count.value) %}{{ '<|video|>' }}{% endfor %}{% if has_subtitle %}{{ messages[0]['content'] }}{% endif %}{% for message in messages %}{% set role = message['role'].lower() %}{% if role == 'subtitle' %}{% continue %}{% endif %}{% set conv_index = loop.index - (1 if has_subtitle else 0) %}{%- if (conv_index % 2 == 1 and role != 'user') or (conv_index % 2 == 0 and role != 'assistant') -%}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{%- endif -%}{% if message['content'] is string %}{% set text_content = message['content'] %}{% else %}{% set m = namespace(text='') %}{% for content in message['content'] %}{% if content['type'] == 'text' %}{% if content['style'] is defined and content['style'] not in DEMO_STYLES %}{% set seg = content['style'] ~ ': ' ~ content['text'] %}{% else %}{% set seg = content['text'] %}{% endif %}{% set m.text = m.text ~ ('' if not m.text else ' ') ~ seg %}{% endif %}{% endfor %}{% set text_content = m.text %}{% endif %}{% if role == 'user' %}{% if not (has_subtitle and loop.index == 2) and not (not has_subtitle and loop.first) %}{{ '<|im_end|>\\n' }}{% endif %}{{ '<|im_start|>user\\n' }}{{ text_content }}{{ '<|im_end|>\\n' }}{% else %} {# assistant #}{{ '<|im_start|>assistant\\n' }}{{ text_content }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\\n' }}{% endif %}",
"model_type": "molmo2",
"tokenizer_config": {
"bos_token": "<|im_end|>",
"eos_token": "<|im_end|>",
"pad_token": "<|endoftext|>",
"unk_token": null
}
},
"createdAt": "2025-12-14T22:55:51.000Z",
"disabled": false,
"downloads": 58102,
"gated": false,
"id": "allenai/Molmo2-4B",
"lastModified": "2026-01-23T01:03:22.000Z",
"library_name": "transformers",
"likes": 54,
"model-index": null,
"modelId": "allenai/Molmo2-4B",
"pipeline_tag": "image-text-to-text",
"private": false,
"safetensors": {
"parameters": {
"F32": 4850869200
},
"total": 4850869200
},
"sha": "042abfa7a38879a376cec03d949eff0aefaa0600",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "README.md"
},
{
"rfilename": "added_tokens.json"
},
{
"rfilename": "chat_template.jinja"
},
{
"rfilename": "config.json"
},
{
"rfilename": "configuration_molmo2.py"
},
{
"rfilename": "generation_config.json"
},
{
"rfilename": "image_processing_molmo2.py"
},
{
"rfilename": "merges.txt"
},
{
"rfilename": "model-00001-of-00004.safetensors"
},
{
"rfilename": "model-00002-of-00004.safetensors"
},
{
"rfilename": "model-00003-of-00004.safetensors"
},
{
"rfilename": "model-00004-of-00004.safetensors"
},
{
"rfilename": "model.safetensors.index.json"
},
{
"rfilename": "modeling_molmo2.py"
},
{
"rfilename": "molmo_2_logo_RGB.png"
},
{
"rfilename": "preprocessor_config.json"
},
{
"rfilename": "processing_molmo2.py"
},
{
"rfilename": "processor_config.json"
},
{
"rfilename": "special_tokens_map.json"
},
{
"rfilename": "tokenizer.json"
},
{
"rfilename": "tokenizer_config.json"
},
{
"rfilename": "video_preprocessor_config.json"
},
{
"rfilename": "video_processing_molmo2.py"
},
{
"rfilename": "vocab.json"
}
],
"spaces": [
"aquanode/gpu-vram-calculator"
],
"tags": [
"transformers",
"safetensors",
"molmo2",
"image-text-to-text",
"multimodal",
"olmo",
"molmo",
"conversational",
"custom_code",
"en",
"dataset:allenai/Molmo2-Cap",
"dataset:allenai/Molmo2-VideoCapQA",
"dataset:allenai/Molmo2-VideoSubtitleQA",
"dataset:allenai/Molmo2-AskModelAnything",
"dataset:allenai/Molmo2-VideoPoint",
"dataset:allenai/Molmo2-VideoTrack",
"dataset:allenai/Molmo2-MultiImageQA",
"dataset:allenai/Molmo2-SynMultiImageQA",
"dataset:allenai/Molmo2-MultiImagePoint",
"base_model:Qwen/Qwen3-4B-Instruct-2507",
"base_model:finetune:Qwen/Qwen3-4B-Instruct-2507",
"license:apache-2.0",
"region:us"
],
"transformersInfo": {
"auto_model": "AutoModelForImageTextToText",
"custom_class": "modeling_molmo2.Molmo2ForConditionalGeneration",
"pipeline_tag": "image-text-to-text"
},
"usedStorage": 19415051449,
"widgetData": [
{
"text": "Hi, what can you help me with?"
},
{
"text": "What is 84 * 3 / 2?"
},
{
"text": "Tell me an interesting fact about the universe!"
},
{
"text": "Explain quantum computing in simple terms."
}
]
} | — | ||||
| Base base | GGUF quantisations | allenai/Molmo2-4Breceipt
What the source handed over{
"_id": "6abaa26c4f2c2ba1836b05f0",
"author": "mu2solutions",
"cardData": {
"base_model": "allenai/Molmo2-4B",
"license": "apache-2.0",
"pipeline_tag": "image-text-to-text",
"tags": [
"gguf",
"llama.cpp",
"allenai",
"molmo",
"vision",
"image-text-to-text"
]
},
"createdAt": "2026-09-28T17:22:52.000Z",
"downloads": 117,
"gated": false,
"id": "mu2solutions/Molmo2-4B-GGUF",
"lastModified": "2026-09-28T17:24:11.000Z",
"likes": 0,
"modelId": "mu2solutions/Molmo2-4B-GGUF",
"pipeline_tag": "image-text-to-text",
"private": false,
"sha": "d3c8673e31ef68266e7396c45d13b404bf499389",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "Molmo2-4B-mmproj-F16.gguf"
},
{
"rfilename": "Molmo2-4B-text-Q4_K_M.gguf"
},
{
"rfilename": "README.md"
},
{
"rfilename": "SHA256SUMS.txt"
}
],
"tags": [
"gguf",
"llama.cpp",
"allenai",
"molmo",
"vision",
"image-text-to-text",
"base_model:allenai/Molmo2-4B",
"base_model:quantized:allenai/Molmo2-4B",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
]
} | — | ||||
| Downloads downloads not compared | GGUF quantisations | 117receipt
What the source handed over{
"_id": "6abaa26c4f2c2ba1836b05f0",
"author": "mu2solutions",
"cardData": {
"base_model": "allenai/Molmo2-4B",
"license": "apache-2.0",
"pipeline_tag": "image-text-to-text",
"tags": [
"gguf",
"llama.cpp",
"allenai",
"molmo",
"vision",
"image-text-to-text"
]
},
"createdAt": "2026-09-28T17:22:52.000Z",
"downloads": 117,
"gated": false,
"id": "mu2solutions/Molmo2-4B-GGUF",
"lastModified": "2026-09-28T17:24:11.000Z",
"likes": 0,
"modelId": "mu2solutions/Molmo2-4B-GGUF",
"pipeline_tag": "image-text-to-text",
"private": false,
"sha": "d3c8673e31ef68266e7396c45d13b404bf499389",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "Molmo2-4B-mmproj-F16.gguf"
},
{
"rfilename": "Molmo2-4B-text-Q4_K_M.gguf"
},
{
"rfilename": "README.md"
},
{
"rfilename": "SHA256SUMS.txt"
}
],
"tags": [
"gguf",
"llama.cpp",
"allenai",
"molmo",
"vision",
"image-text-to-text",
"base_model:allenai/Molmo2-4B",
"base_model:quantized:allenai/Molmo2-4B",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
]
} | — | ||||
| Downloads downloads not compared | Hugging Face models | 58102receipt
What the source handed over{
"_asked": "allenai/Molmo2-4B",
"_id": "693f4077d9c3e9aae0b943b1",
"author": "allenai",
"cardData": {
"base_model": [
"google/siglip-so400m-patch14-384",
"Qwen/Qwen3-4B-Instruct-2507"
],
"datasets": [
"allenai/Molmo2-Cap",
"allenai/Molmo2-VideoCapQA",
"allenai/Molmo2-VideoSubtitleQA",
"allenai/Molmo2-AskModelAnything",
"allenai/Molmo2-VideoPoint",
"allenai/Molmo2-VideoTrack",
"allenai/Molmo2-MultiImageQA",
"allenai/Molmo2-SynMultiImageQA",
"allenai/Molmo2-MultiImagePoint"
],
"language": [
"en"
],
"library_name": "transformers",
"license": "apache-2.0",
"pipeline_tag": "image-text-to-text",
"tags": [
"multimodal",
"olmo",
"molmo",
"molmo2"
]
},
"config": {
"architectures": [
"Molmo2ForConditionalGeneration"
],
"auto_map": {
"AutoConfig": "configuration_molmo2.Molmo2Config",
"AutoModelForImageTextToText": "modeling_molmo2.Molmo2ForConditionalGeneration"
},
"chat_template_jinja": "{% set DEMO_STYLES = ['point_count','pointing','cosyn_point','user_qa','long_caption','short_caption','video_long_caption','video_short_caption','video_point_track_per_frame','video_point_track_start_end','video_point_track_all_frames','video_single_point_track_start_end','video_transcript','video_clip_caption_start_end','video_clip_caption_start_end_in_seconds','video_clip_transcript_start_end','video_clip_transcript_start_end_in_seconds','video_frame_caption_timestamp','video_frame_caption_timestamp_in_seconds','correction_qa','text_sft','video_point','video_point_count','video_count','video_count_point','multi_image_pointing','multi_image_counting','multi_image_point_then_count','multi_image_count_then_point','demo','a_okvqa_mc','ai2_diagram_no_letter','ai2_diagram','science_qa','multi_image_mc','multi_image_mc_exp','mantis_instruct_mc','video_multiple_choice','video_multiple_choice_count_without_pointing','video_multiple_choice_multiple_correct','video_multiple_choice_w_subtitle'] %}{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% set has_subtitle = messages and messages[0]['role'].lower() == 'subtitle' %}{% for message in messages %}{% if message['content'] is not string %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% elif content['type'] == 'video' or 'video' in content or 'video_url' in content %}{% set video_count.value = video_count.value + 1 %}{% endif %}{% endfor %}{% endif %}{% endfor %}{% if image_count.value == 1 %}{{ '<|image|>' }}{% elif image_count.value > 1 %}{% for i in range(image_count.value) %}{{ 'Image ' ~ (i + 1) ~ '<|image|>' }}{% endfor %}{% endif %}{% for _ in range(video_count.value) %}{{ '<|video|>' }}{% endfor %}{% if has_subtitle %}{{ messages[0]['content'] }}{% endif %}{% for message in messages %}{% set role = message['role'].lower() %}{% if role == 'subtitle' %}{% continue %}{% endif %}{% set conv_index = loop.index - (1 if has_subtitle else 0) %}{%- if (conv_index % 2 == 1 and role != 'user') or (conv_index % 2 == 0 and role != 'assistant') -%}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{%- endif -%}{% if message['content'] is string %}{% set text_content = message['content'] %}{% else %}{% set m = namespace(text='') %}{% for content in message['content'] %}{% if content['type'] == 'text' %}{% if content['style'] is defined and content['style'] not in DEMO_STYLES %}{% set seg = content['style'] ~ ': ' ~ content['text'] %}{% else %}{% set seg = content['text'] %}{% endif %}{% set m.text = m.text ~ ('' if not m.text else ' ') ~ seg %}{% endif %}{% endfor %}{% set text_content = m.text %}{% endif %}{% if role == 'user' %}{% if not (has_subtitle and loop.index == 2) and not (not has_subtitle and loop.first) %}{{ '<|im_end|>\\n' }}{% endif %}{{ '<|im_start|>user\\n' }}{{ text_content }}{{ '<|im_end|>\\n' }}{% else %} {# assistant #}{{ '<|im_start|>assistant\\n' }}{{ text_content }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\\n' }}{% endif %}",
"model_type": "molmo2",
"tokenizer_config": {
"bos_token": "<|im_end|>",
"eos_token": "<|im_end|>",
"pad_token": "<|endoftext|>",
"unk_token": null
}
},
"createdAt": "2025-12-14T22:55:51.000Z",
"disabled": false,
"downloads": 58102,
"gated": false,
"id": "allenai/Molmo2-4B",
"lastModified": "2026-01-23T01:03:22.000Z",
"library_name": "transformers",
"likes": 54,
"model-index": null,
"modelId": "allenai/Molmo2-4B",
"pipeline_tag": "image-text-to-text",
"private": false,
"safetensors": {
"parameters": {
"F32": 4850869200
},
"total": 4850869200
},
"sha": "042abfa7a38879a376cec03d949eff0aefaa0600",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "README.md"
},
{
"rfilename": "added_tokens.json"
},
{
"rfilename": "chat_template.jinja"
},
{
"rfilename": "config.json"
},
{
"rfilename": "configuration_molmo2.py"
},
{
"rfilename": "generation_config.json"
},
{
"rfilename": "image_processing_molmo2.py"
},
{
"rfilename": "merges.txt"
},
{
"rfilename": "model-00001-of-00004.safetensors"
},
{
"rfilename": "model-00002-of-00004.safetensors"
},
{
"rfilename": "model-00003-of-00004.safetensors"
},
{
"rfilename": "model-00004-of-00004.safetensors"
},
{
"rfilename": "model.safetensors.index.json"
},
{
"rfilename": "modeling_molmo2.py"
},
{
"rfilename": "molmo_2_logo_RGB.png"
},
{
"rfilename": "preprocessor_config.json"
},
{
"rfilename": "processing_molmo2.py"
},
{
"rfilename": "processor_config.json"
},
{
"rfilename": "special_tokens_map.json"
},
{
"rfilename": "tokenizer.json"
},
{
"rfilename": "tokenizer_config.json"
},
{
"rfilename": "video_preprocessor_config.json"
},
{
"rfilename": "video_processing_molmo2.py"
},
{
"rfilename": "vocab.json"
}
],
"spaces": [
"aquanode/gpu-vram-calculator"
],
"tags": [
"transformers",
"safetensors",
"molmo2",
"image-text-to-text",
"multimodal",
"olmo",
"molmo",
"conversational",
"custom_code",
"en",
"dataset:allenai/Molmo2-Cap",
"dataset:allenai/Molmo2-VideoCapQA",
"dataset:allenai/Molmo2-VideoSubtitleQA",
"dataset:allenai/Molmo2-AskModelAnything",
"dataset:allenai/Molmo2-VideoPoint",
"dataset:allenai/Molmo2-VideoTrack",
"dataset:allenai/Molmo2-MultiImageQA",
"dataset:allenai/Molmo2-SynMultiImageQA",
"dataset:allenai/Molmo2-MultiImagePoint",
"base_model:Qwen/Qwen3-4B-Instruct-2507",
"base_model:finetune:Qwen/Qwen3-4B-Instruct-2507",
"license:apache-2.0",
"region:us"
],
"transformersInfo": {
"auto_model": "AutoModelForImageTextToText",
"custom_class": "modeling_molmo2.Molmo2ForConditionalGeneration",
"pipeline_tag": "image-text-to-text"
},
"usedStorage": 19415051449,
"widgetData": [
{
"text": "Hi, what can you help me with?"
},
{
"text": "What is 84 * 3 / 2?"
},
{
"text": "Tell me an interesting fact about the universe!"
},
{
"text": "Explain quantum computing in simple terms."
}
]
} | — | ||||
| Gated gated | Hugging Face models | falsereceipt
What the source handed over{
"_asked": "allenai/Molmo2-4B",
"_id": "693f4077d9c3e9aae0b943b1",
"author": "allenai",
"cardData": {
"base_model": [
"google/siglip-so400m-patch14-384",
"Qwen/Qwen3-4B-Instruct-2507"
],
"datasets": [
"allenai/Molmo2-Cap",
"allenai/Molmo2-VideoCapQA",
"allenai/Molmo2-VideoSubtitleQA",
"allenai/Molmo2-AskModelAnything",
"allenai/Molmo2-VideoPoint",
"allenai/Molmo2-VideoTrack",
"allenai/Molmo2-MultiImageQA",
"allenai/Molmo2-SynMultiImageQA",
"allenai/Molmo2-MultiImagePoint"
],
"language": [
"en"
],
"library_name": "transformers",
"license": "apache-2.0",
"pipeline_tag": "image-text-to-text",
"tags": [
"multimodal",
"olmo",
"molmo",
"molmo2"
]
},
"config": {
"architectures": [
"Molmo2ForConditionalGeneration"
],
"auto_map": {
"AutoConfig": "configuration_molmo2.Molmo2Config",
"AutoModelForImageTextToText": "modeling_molmo2.Molmo2ForConditionalGeneration"
},
"chat_template_jinja": "{% set DEMO_STYLES = ['point_count','pointing','cosyn_point','user_qa','long_caption','short_caption','video_long_caption','video_short_caption','video_point_track_per_frame','video_point_track_start_end','video_point_track_all_frames','video_single_point_track_start_end','video_transcript','video_clip_caption_start_end','video_clip_caption_start_end_in_seconds','video_clip_transcript_start_end','video_clip_transcript_start_end_in_seconds','video_frame_caption_timestamp','video_frame_caption_timestamp_in_seconds','correction_qa','text_sft','video_point','video_point_count','video_count','video_count_point','multi_image_pointing','multi_image_counting','multi_image_point_then_count','multi_image_count_then_point','demo','a_okvqa_mc','ai2_diagram_no_letter','ai2_diagram','science_qa','multi_image_mc','multi_image_mc_exp','mantis_instruct_mc','video_multiple_choice','video_multiple_choice_count_without_pointing','video_multiple_choice_multiple_correct','video_multiple_choice_w_subtitle'] %}{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% set has_subtitle = messages and messages[0]['role'].lower() == 'subtitle' %}{% for message in messages %}{% if message['content'] is not string %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% elif content['type'] == 'video' or 'video' in content or 'video_url' in content %}{% set video_count.value = video_count.value + 1 %}{% endif %}{% endfor %}{% endif %}{% endfor %}{% if image_count.value == 1 %}{{ '<|image|>' }}{% elif image_count.value > 1 %}{% for i in range(image_count.value) %}{{ 'Image ' ~ (i + 1) ~ '<|image|>' }}{% endfor %}{% endif %}{% for _ in range(video_count.value) %}{{ '<|video|>' }}{% endfor %}{% if has_subtitle %}{{ messages[0]['content'] }}{% endif %}{% for message in messages %}{% set role = message['role'].lower() %}{% if role == 'subtitle' %}{% continue %}{% endif %}{% set conv_index = loop.index - (1 if has_subtitle else 0) %}{%- if (conv_index % 2 == 1 and role != 'user') or (conv_index % 2 == 0 and role != 'assistant') -%}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{%- endif -%}{% if message['content'] is string %}{% set text_content = message['content'] %}{% else %}{% set m = namespace(text='') %}{% for content in message['content'] %}{% if content['type'] == 'text' %}{% if content['style'] is defined and content['style'] not in DEMO_STYLES %}{% set seg = content['style'] ~ ': ' ~ content['text'] %}{% else %}{% set seg = content['text'] %}{% endif %}{% set m.text = m.text ~ ('' if not m.text else ' ') ~ seg %}{% endif %}{% endfor %}{% set text_content = m.text %}{% endif %}{% if role == 'user' %}{% if not (has_subtitle and loop.index == 2) and not (not has_subtitle and loop.first) %}{{ '<|im_end|>\\n' }}{% endif %}{{ '<|im_start|>user\\n' }}{{ text_content }}{{ '<|im_end|>\\n' }}{% else %} {# assistant #}{{ '<|im_start|>assistant\\n' }}{{ text_content }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\\n' }}{% endif %}",
"model_type": "molmo2",
"tokenizer_config": {
"bos_token": "<|im_end|>",
"eos_token": "<|im_end|>",
"pad_token": "<|endoftext|>",
"unk_token": null
}
},
"createdAt": "2025-12-14T22:55:51.000Z",
"disabled": false,
"downloads": 58102,
"gated": false,
"id": "allenai/Molmo2-4B",
"lastModified": "2026-01-23T01:03:22.000Z",
"library_name": "transformers",
"likes": 54,
"model-index": null,
"modelId": "allenai/Molmo2-4B",
"pipeline_tag": "image-text-to-text",
"private": false,
"safetensors": {
"parameters": {
"F32": 4850869200
},
"total": 4850869200
},
"sha": "042abfa7a38879a376cec03d949eff0aefaa0600",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "README.md"
},
{
"rfilename": "added_tokens.json"
},
{
"rfilename": "chat_template.jinja"
},
{
"rfilename": "config.json"
},
{
"rfilename": "configuration_molmo2.py"
},
{
"rfilename": "generation_config.json"
},
{
"rfilename": "image_processing_molmo2.py"
},
{
"rfilename": "merges.txt"
},
{
"rfilename": "model-00001-of-00004.safetensors"
},
{
"rfilename": "model-00002-of-00004.safetensors"
},
{
"rfilename": "model-00003-of-00004.safetensors"
},
{
"rfilename": "model-00004-of-00004.safetensors"
},
{
"rfilename": "model.safetensors.index.json"
},
{
"rfilename": "modeling_molmo2.py"
},
{
"rfilename": "molmo_2_logo_RGB.png"
},
{
"rfilename": "preprocessor_config.json"
},
{
"rfilename": "processing_molmo2.py"
},
{
"rfilename": "processor_config.json"
},
{
"rfilename": "special_tokens_map.json"
},
{
"rfilename": "tokenizer.json"
},
{
"rfilename": "tokenizer_config.json"
},
{
"rfilename": "video_preprocessor_config.json"
},
{
"rfilename": "video_processing_molmo2.py"
},
{
"rfilename": "vocab.json"
}
],
"spaces": [
"aquanode/gpu-vram-calculator"
],
"tags": [
"transformers",
"safetensors",
"molmo2",
"image-text-to-text",
"multimodal",
"olmo",
"molmo",
"conversational",
"custom_code",
"en",
"dataset:allenai/Molmo2-Cap",
"dataset:allenai/Molmo2-VideoCapQA",
"dataset:allenai/Molmo2-VideoSubtitleQA",
"dataset:allenai/Molmo2-AskModelAnything",
"dataset:allenai/Molmo2-VideoPoint",
"dataset:allenai/Molmo2-VideoTrack",
"dataset:allenai/Molmo2-MultiImageQA",
"dataset:allenai/Molmo2-SynMultiImageQA",
"dataset:allenai/Molmo2-MultiImagePoint",
"base_model:Qwen/Qwen3-4B-Instruct-2507",
"base_model:finetune:Qwen/Qwen3-4B-Instruct-2507",
"license:apache-2.0",
"region:us"
],
"transformersInfo": {
"auto_model": "AutoModelForImageTextToText",
"custom_class": "modeling_molmo2.Molmo2ForConditionalGeneration",
"pipeline_tag": "image-text-to-text"
},
"usedStorage": 19415051449,
"widgetData": [
{
"text": "Hi, what can you help me with?"
},
{
"text": "What is 84 * 3 / 2?"
},
{
"text": "Tell me an interesting fact about the universe!"
},
{
"text": "Explain quantum computing in simple terms."
}
]
} | — | ||||
| Licence licence | GGUF quantisations | apache-2.0receipt
What the source handed over{
"_id": "6abaa26c4f2c2ba1836b05f0",
"author": "mu2solutions",
"cardData": {
"base_model": "allenai/Molmo2-4B",
"license": "apache-2.0",
"pipeline_tag": "image-text-to-text",
"tags": [
"gguf",
"llama.cpp",
"allenai",
"molmo",
"vision",
"image-text-to-text"
]
},
"createdAt": "2026-09-28T17:22:52.000Z",
"downloads": 117,
"gated": false,
"id": "mu2solutions/Molmo2-4B-GGUF",
"lastModified": "2026-09-28T17:24:11.000Z",
"likes": 0,
"modelId": "mu2solutions/Molmo2-4B-GGUF",
"pipeline_tag": "image-text-to-text",
"private": false,
"sha": "d3c8673e31ef68266e7396c45d13b404bf499389",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "Molmo2-4B-mmproj-F16.gguf"
},
{
"rfilename": "Molmo2-4B-text-Q4_K_M.gguf"
},
{
"rfilename": "README.md"
},
{
"rfilename": "SHA256SUMS.txt"
}
],
"tags": [
"gguf",
"llama.cpp",
"allenai",
"molmo",
"vision",
"image-text-to-text",
"base_model:allenai/Molmo2-4B",
"base_model:quantized:allenai/Molmo2-4B",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
]
} | — | ||||
| Licence licence | Hugging Face models | apache-2.0receipt
What the source handed over{
"_asked": "allenai/Molmo2-4B",
"_id": "693f4077d9c3e9aae0b943b1",
"author": "allenai",
"cardData": {
"base_model": [
"google/siglip-so400m-patch14-384",
"Qwen/Qwen3-4B-Instruct-2507"
],
"datasets": [
"allenai/Molmo2-Cap",
"allenai/Molmo2-VideoCapQA",
"allenai/Molmo2-VideoSubtitleQA",
"allenai/Molmo2-AskModelAnything",
"allenai/Molmo2-VideoPoint",
"allenai/Molmo2-VideoTrack",
"allenai/Molmo2-MultiImageQA",
"allenai/Molmo2-SynMultiImageQA",
"allenai/Molmo2-MultiImagePoint"
],
"language": [
"en"
],
"library_name": "transformers",
"license": "apache-2.0",
"pipeline_tag": "image-text-to-text",
"tags": [
"multimodal",
"olmo",
"molmo",
"molmo2"
]
},
"config": {
"architectures": [
"Molmo2ForConditionalGeneration"
],
"auto_map": {
"AutoConfig": "configuration_molmo2.Molmo2Config",
"AutoModelForImageTextToText": "modeling_molmo2.Molmo2ForConditionalGeneration"
},
"chat_template_jinja": "{% set DEMO_STYLES = ['point_count','pointing','cosyn_point','user_qa','long_caption','short_caption','video_long_caption','video_short_caption','video_point_track_per_frame','video_point_track_start_end','video_point_track_all_frames','video_single_point_track_start_end','video_transcript','video_clip_caption_start_end','video_clip_caption_start_end_in_seconds','video_clip_transcript_start_end','video_clip_transcript_start_end_in_seconds','video_frame_caption_timestamp','video_frame_caption_timestamp_in_seconds','correction_qa','text_sft','video_point','video_point_count','video_count','video_count_point','multi_image_pointing','multi_image_counting','multi_image_point_then_count','multi_image_count_then_point','demo','a_okvqa_mc','ai2_diagram_no_letter','ai2_diagram','science_qa','multi_image_mc','multi_image_mc_exp','mantis_instruct_mc','video_multiple_choice','video_multiple_choice_count_without_pointing','video_multiple_choice_multiple_correct','video_multiple_choice_w_subtitle'] %}{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% set has_subtitle = messages and messages[0]['role'].lower() == 'subtitle' %}{% for message in messages %}{% if message['content'] is not string %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% elif content['type'] == 'video' or 'video' in content or 'video_url' in content %}{% set video_count.value = video_count.value + 1 %}{% endif %}{% endfor %}{% endif %}{% endfor %}{% if image_count.value == 1 %}{{ '<|image|>' }}{% elif image_count.value > 1 %}{% for i in range(image_count.value) %}{{ 'Image ' ~ (i + 1) ~ '<|image|>' }}{% endfor %}{% endif %}{% for _ in range(video_count.value) %}{{ '<|video|>' }}{% endfor %}{% if has_subtitle %}{{ messages[0]['content'] }}{% endif %}{% for message in messages %}{% set role = message['role'].lower() %}{% if role == 'subtitle' %}{% continue %}{% endif %}{% set conv_index = loop.index - (1 if has_subtitle else 0) %}{%- if (conv_index % 2 == 1 and role != 'user') or (conv_index % 2 == 0 and role != 'assistant') -%}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{%- endif -%}{% if message['content'] is string %}{% set text_content = message['content'] %}{% else %}{% set m = namespace(text='') %}{% for content in message['content'] %}{% if content['type'] == 'text' %}{% if content['style'] is defined and content['style'] not in DEMO_STYLES %}{% set seg = content['style'] ~ ': ' ~ content['text'] %}{% else %}{% set seg = content['text'] %}{% endif %}{% set m.text = m.text ~ ('' if not m.text else ' ') ~ seg %}{% endif %}{% endfor %}{% set text_content = m.text %}{% endif %}{% if role == 'user' %}{% if not (has_subtitle and loop.index == 2) and not (not has_subtitle and loop.first) %}{{ '<|im_end|>\\n' }}{% endif %}{{ '<|im_start|>user\\n' }}{{ text_content }}{{ '<|im_end|>\\n' }}{% else %} {# assistant #}{{ '<|im_start|>assistant\\n' }}{{ text_content }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\\n' }}{% endif %}",
"model_type": "molmo2",
"tokenizer_config": {
"bos_token": "<|im_end|>",
"eos_token": "<|im_end|>",
"pad_token": "<|endoftext|>",
"unk_token": null
}
},
"createdAt": "2025-12-14T22:55:51.000Z",
"disabled": false,
"downloads": 58102,
"gated": false,
"id": "allenai/Molmo2-4B",
"lastModified": "2026-01-23T01:03:22.000Z",
"library_name": "transformers",
"likes": 54,
"model-index": null,
"modelId": "allenai/Molmo2-4B",
"pipeline_tag": "image-text-to-text",
"private": false,
"safetensors": {
"parameters": {
"F32": 4850869200
},
"total": 4850869200
},
"sha": "042abfa7a38879a376cec03d949eff0aefaa0600",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "README.md"
},
{
"rfilename": "added_tokens.json"
},
{
"rfilename": "chat_template.jinja"
},
{
"rfilename": "config.json"
},
{
"rfilename": "configuration_molmo2.py"
},
{
"rfilename": "generation_config.json"
},
{
"rfilename": "image_processing_molmo2.py"
},
{
"rfilename": "merges.txt"
},
{
"rfilename": "model-00001-of-00004.safetensors"
},
{
"rfilename": "model-00002-of-00004.safetensors"
},
{
"rfilename": "model-00003-of-00004.safetensors"
},
{
"rfilename": "model-00004-of-00004.safetensors"
},
{
"rfilename": "model.safetensors.index.json"
},
{
"rfilename": "modeling_molmo2.py"
},
{
"rfilename": "molmo_2_logo_RGB.png"
},
{
"rfilename": "preprocessor_config.json"
},
{
"rfilename": "processing_molmo2.py"
},
{
"rfilename": "processor_config.json"
},
{
"rfilename": "special_tokens_map.json"
},
{
"rfilename": "tokenizer.json"
},
{
"rfilename": "tokenizer_config.json"
},
{
"rfilename": "video_preprocessor_config.json"
},
{
"rfilename": "video_processing_molmo2.py"
},
{
"rfilename": "vocab.json"
}
],
"spaces": [
"aquanode/gpu-vram-calculator"
],
"tags": [
"transformers",
"safetensors",
"molmo2",
"image-text-to-text",
"multimodal",
"olmo",
"molmo",
"conversational",
"custom_code",
"en",
"dataset:allenai/Molmo2-Cap",
"dataset:allenai/Molmo2-VideoCapQA",
"dataset:allenai/Molmo2-VideoSubtitleQA",
"dataset:allenai/Molmo2-AskModelAnything",
"dataset:allenai/Molmo2-VideoPoint",
"dataset:allenai/Molmo2-VideoTrack",
"dataset:allenai/Molmo2-MultiImageQA",
"dataset:allenai/Molmo2-SynMultiImageQA",
"dataset:allenai/Molmo2-MultiImagePoint",
"base_model:Qwen/Qwen3-4B-Instruct-2507",
"base_model:finetune:Qwen/Qwen3-4B-Instruct-2507",
"license:apache-2.0",
"region:us"
],
"transformersInfo": {
"auto_model": "AutoModelForImageTextToText",
"custom_class": "modeling_molmo2.Molmo2ForConditionalGeneration",
"pipeline_tag": "image-text-to-text"
},
"usedStorage": 19415051449,
"widgetData": [
{
"text": "Hi, what can you help me with?"
},
{
"text": "What is 84 * 3 / 2?"
},
{
"text": "Tell me an interesting fact about the universe!"
},
{
"text": "Explain quantum computing in simple terms."
}
]
} | — | ||||
| Likes likes not compared | GGUF quantisations | 0receipt
What the source handed over{
"_id": "6abaa26c4f2c2ba1836b05f0",
"author": "mu2solutions",
"cardData": {
"base_model": "allenai/Molmo2-4B",
"license": "apache-2.0",
"pipeline_tag": "image-text-to-text",
"tags": [
"gguf",
"llama.cpp",
"allenai",
"molmo",
"vision",
"image-text-to-text"
]
},
"createdAt": "2026-09-28T17:22:52.000Z",
"downloads": 117,
"gated": false,
"id": "mu2solutions/Molmo2-4B-GGUF",
"lastModified": "2026-09-28T17:24:11.000Z",
"likes": 0,
"modelId": "mu2solutions/Molmo2-4B-GGUF",
"pipeline_tag": "image-text-to-text",
"private": false,
"sha": "d3c8673e31ef68266e7396c45d13b404bf499389",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "Molmo2-4B-mmproj-F16.gguf"
},
{
"rfilename": "Molmo2-4B-text-Q4_K_M.gguf"
},
{
"rfilename": "README.md"
},
{
"rfilename": "SHA256SUMS.txt"
}
],
"tags": [
"gguf",
"llama.cpp",
"allenai",
"molmo",
"vision",
"image-text-to-text",
"base_model:allenai/Molmo2-4B",
"base_model:quantized:allenai/Molmo2-4B",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
]
} | — | ||||
| Likes likes not compared | Hugging Face models | 54receipt
What the source handed over{
"_asked": "allenai/Molmo2-4B",
"_id": "693f4077d9c3e9aae0b943b1",
"author": "allenai",
"cardData": {
"base_model": [
"google/siglip-so400m-patch14-384",
"Qwen/Qwen3-4B-Instruct-2507"
],
"datasets": [
"allenai/Molmo2-Cap",
"allenai/Molmo2-VideoCapQA",
"allenai/Molmo2-VideoSubtitleQA",
"allenai/Molmo2-AskModelAnything",
"allenai/Molmo2-VideoPoint",
"allenai/Molmo2-VideoTrack",
"allenai/Molmo2-MultiImageQA",
"allenai/Molmo2-SynMultiImageQA",
"allenai/Molmo2-MultiImagePoint"
],
"language": [
"en"
],
"library_name": "transformers",
"license": "apache-2.0",
"pipeline_tag": "image-text-to-text",
"tags": [
"multimodal",
"olmo",
"molmo",
"molmo2"
]
},
"config": {
"architectures": [
"Molmo2ForConditionalGeneration"
],
"auto_map": {
"AutoConfig": "configuration_molmo2.Molmo2Config",
"AutoModelForImageTextToText": "modeling_molmo2.Molmo2ForConditionalGeneration"
},
"chat_template_jinja": "{% set DEMO_STYLES = ['point_count','pointing','cosyn_point','user_qa','long_caption','short_caption','video_long_caption','video_short_caption','video_point_track_per_frame','video_point_track_start_end','video_point_track_all_frames','video_single_point_track_start_end','video_transcript','video_clip_caption_start_end','video_clip_caption_start_end_in_seconds','video_clip_transcript_start_end','video_clip_transcript_start_end_in_seconds','video_frame_caption_timestamp','video_frame_caption_timestamp_in_seconds','correction_qa','text_sft','video_point','video_point_count','video_count','video_count_point','multi_image_pointing','multi_image_counting','multi_image_point_then_count','multi_image_count_then_point','demo','a_okvqa_mc','ai2_diagram_no_letter','ai2_diagram','science_qa','multi_image_mc','multi_image_mc_exp','mantis_instruct_mc','video_multiple_choice','video_multiple_choice_count_without_pointing','video_multiple_choice_multiple_correct','video_multiple_choice_w_subtitle'] %}{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% set has_subtitle = messages and messages[0]['role'].lower() == 'subtitle' %}{% for message in messages %}{% if message['content'] is not string %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% elif content['type'] == 'video' or 'video' in content or 'video_url' in content %}{% set video_count.value = video_count.value + 1 %}{% endif %}{% endfor %}{% endif %}{% endfor %}{% if image_count.value == 1 %}{{ '<|image|>' }}{% elif image_count.value > 1 %}{% for i in range(image_count.value) %}{{ 'Image ' ~ (i + 1) ~ '<|image|>' }}{% endfor %}{% endif %}{% for _ in range(video_count.value) %}{{ '<|video|>' }}{% endfor %}{% if has_subtitle %}{{ messages[0]['content'] }}{% endif %}{% for message in messages %}{% set role = message['role'].lower() %}{% if role == 'subtitle' %}{% continue %}{% endif %}{% set conv_index = loop.index - (1 if has_subtitle else 0) %}{%- if (conv_index % 2 == 1 and role != 'user') or (conv_index % 2 == 0 and role != 'assistant') -%}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{%- endif -%}{% if message['content'] is string %}{% set text_content = message['content'] %}{% else %}{% set m = namespace(text='') %}{% for content in message['content'] %}{% if content['type'] == 'text' %}{% if content['style'] is defined and content['style'] not in DEMO_STYLES %}{% set seg = content['style'] ~ ': ' ~ content['text'] %}{% else %}{% set seg = content['text'] %}{% endif %}{% set m.text = m.text ~ ('' if not m.text else ' ') ~ seg %}{% endif %}{% endfor %}{% set text_content = m.text %}{% endif %}{% if role == 'user' %}{% if not (has_subtitle and loop.index == 2) and not (not has_subtitle and loop.first) %}{{ '<|im_end|>\\n' }}{% endif %}{{ '<|im_start|>user\\n' }}{{ text_content }}{{ '<|im_end|>\\n' }}{% else %} {# assistant #}{{ '<|im_start|>assistant\\n' }}{{ text_content }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\\n' }}{% endif %}",
"model_type": "molmo2",
"tokenizer_config": {
"bos_token": "<|im_end|>",
"eos_token": "<|im_end|>",
"pad_token": "<|endoftext|>",
"unk_token": null
}
},
"createdAt": "2025-12-14T22:55:51.000Z",
"disabled": false,
"downloads": 58102,
"gated": false,
"id": "allenai/Molmo2-4B",
"lastModified": "2026-01-23T01:03:22.000Z",
"library_name": "transformers",
"likes": 54,
"model-index": null,
"modelId": "allenai/Molmo2-4B",
"pipeline_tag": "image-text-to-text",
"private": false,
"safetensors": {
"parameters": {
"F32": 4850869200
},
"total": 4850869200
},
"sha": "042abfa7a38879a376cec03d949eff0aefaa0600",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "README.md"
},
{
"rfilename": "added_tokens.json"
},
{
"rfilename": "chat_template.jinja"
},
{
"rfilename": "config.json"
},
{
"rfilename": "configuration_molmo2.py"
},
{
"rfilename": "generation_config.json"
},
{
"rfilename": "image_processing_molmo2.py"
},
{
"rfilename": "merges.txt"
},
{
"rfilename": "model-00001-of-00004.safetensors"
},
{
"rfilename": "model-00002-of-00004.safetensors"
},
{
"rfilename": "model-00003-of-00004.safetensors"
},
{
"rfilename": "model-00004-of-00004.safetensors"
},
{
"rfilename": "model.safetensors.index.json"
},
{
"rfilename": "modeling_molmo2.py"
},
{
"rfilename": "molmo_2_logo_RGB.png"
},
{
"rfilename": "preprocessor_config.json"
},
{
"rfilename": "processing_molmo2.py"
},
{
"rfilename": "processor_config.json"
},
{
"rfilename": "special_tokens_map.json"
},
{
"rfilename": "tokenizer.json"
},
{
"rfilename": "tokenizer_config.json"
},
{
"rfilename": "video_preprocessor_config.json"
},
{
"rfilename": "video_processing_molmo2.py"
},
{
"rfilename": "vocab.json"
}
],
"spaces": [
"aquanode/gpu-vram-calculator"
],
"tags": [
"transformers",
"safetensors",
"molmo2",
"image-text-to-text",
"multimodal",
"olmo",
"molmo",
"conversational",
"custom_code",
"en",
"dataset:allenai/Molmo2-Cap",
"dataset:allenai/Molmo2-VideoCapQA",
"dataset:allenai/Molmo2-VideoSubtitleQA",
"dataset:allenai/Molmo2-AskModelAnything",
"dataset:allenai/Molmo2-VideoPoint",
"dataset:allenai/Molmo2-VideoTrack",
"dataset:allenai/Molmo2-MultiImageQA",
"dataset:allenai/Molmo2-SynMultiImageQA",
"dataset:allenai/Molmo2-MultiImagePoint",
"base_model:Qwen/Qwen3-4B-Instruct-2507",
"base_model:finetune:Qwen/Qwen3-4B-Instruct-2507",
"license:apache-2.0",
"region:us"
],
"transformersInfo": {
"auto_model": "AutoModelForImageTextToText",
"custom_class": "modeling_molmo2.Molmo2ForConditionalGeneration",
"pipeline_tag": "image-text-to-text"
},
"usedStorage": 19415051449,
"widgetData": [
{
"text": "Hi, what can you help me with?"
},
{
"text": "What is 84 * 3 / 2?"
},
{
"text": "Tell me an interesting fact about the universe!"
},
{
"text": "Explain quantum computing in simple terms."
}
]
} | — | ||||
| Task task | Hugging Face models | image-text-to-textreceipt
What the source handed over{
"_asked": "allenai/Molmo2-4B",
"_id": "693f4077d9c3e9aae0b943b1",
"author": "allenai",
"cardData": {
"base_model": [
"google/siglip-so400m-patch14-384",
"Qwen/Qwen3-4B-Instruct-2507"
],
"datasets": [
"allenai/Molmo2-Cap",
"allenai/Molmo2-VideoCapQA",
"allenai/Molmo2-VideoSubtitleQA",
"allenai/Molmo2-AskModelAnything",
"allenai/Molmo2-VideoPoint",
"allenai/Molmo2-VideoTrack",
"allenai/Molmo2-MultiImageQA",
"allenai/Molmo2-SynMultiImageQA",
"allenai/Molmo2-MultiImagePoint"
],
"language": [
"en"
],
"library_name": "transformers",
"license": "apache-2.0",
"pipeline_tag": "image-text-to-text",
"tags": [
"multimodal",
"olmo",
"molmo",
"molmo2"
]
},
"config": {
"architectures": [
"Molmo2ForConditionalGeneration"
],
"auto_map": {
"AutoConfig": "configuration_molmo2.Molmo2Config",
"AutoModelForImageTextToText": "modeling_molmo2.Molmo2ForConditionalGeneration"
},
"chat_template_jinja": "{% set DEMO_STYLES = ['point_count','pointing','cosyn_point','user_qa','long_caption','short_caption','video_long_caption','video_short_caption','video_point_track_per_frame','video_point_track_start_end','video_point_track_all_frames','video_single_point_track_start_end','video_transcript','video_clip_caption_start_end','video_clip_caption_start_end_in_seconds','video_clip_transcript_start_end','video_clip_transcript_start_end_in_seconds','video_frame_caption_timestamp','video_frame_caption_timestamp_in_seconds','correction_qa','text_sft','video_point','video_point_count','video_count','video_count_point','multi_image_pointing','multi_image_counting','multi_image_point_then_count','multi_image_count_then_point','demo','a_okvqa_mc','ai2_diagram_no_letter','ai2_diagram','science_qa','multi_image_mc','multi_image_mc_exp','mantis_instruct_mc','video_multiple_choice','video_multiple_choice_count_without_pointing','video_multiple_choice_multiple_correct','video_multiple_choice_w_subtitle'] %}{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% set has_subtitle = messages and messages[0]['role'].lower() == 'subtitle' %}{% for message in messages %}{% if message['content'] is not string %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% elif content['type'] == 'video' or 'video' in content or 'video_url' in content %}{% set video_count.value = video_count.value + 1 %}{% endif %}{% endfor %}{% endif %}{% endfor %}{% if image_count.value == 1 %}{{ '<|image|>' }}{% elif image_count.value > 1 %}{% for i in range(image_count.value) %}{{ 'Image ' ~ (i + 1) ~ '<|image|>' }}{% endfor %}{% endif %}{% for _ in range(video_count.value) %}{{ '<|video|>' }}{% endfor %}{% if has_subtitle %}{{ messages[0]['content'] }}{% endif %}{% for message in messages %}{% set role = message['role'].lower() %}{% if role == 'subtitle' %}{% continue %}{% endif %}{% set conv_index = loop.index - (1 if has_subtitle else 0) %}{%- if (conv_index % 2 == 1 and role != 'user') or (conv_index % 2 == 0 and role != 'assistant') -%}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{%- endif -%}{% if message['content'] is string %}{% set text_content = message['content'] %}{% else %}{% set m = namespace(text='') %}{% for content in message['content'] %}{% if content['type'] == 'text' %}{% if content['style'] is defined and content['style'] not in DEMO_STYLES %}{% set seg = content['style'] ~ ': ' ~ content['text'] %}{% else %}{% set seg = content['text'] %}{% endif %}{% set m.text = m.text ~ ('' if not m.text else ' ') ~ seg %}{% endif %}{% endfor %}{% set text_content = m.text %}{% endif %}{% if role == 'user' %}{% if not (has_subtitle and loop.index == 2) and not (not has_subtitle and loop.first) %}{{ '<|im_end|>\\n' }}{% endif %}{{ '<|im_start|>user\\n' }}{{ text_content }}{{ '<|im_end|>\\n' }}{% else %} {# assistant #}{{ '<|im_start|>assistant\\n' }}{{ text_content }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\\n' }}{% endif %}",
"model_type": "molmo2",
"tokenizer_config": {
"bos_token": "<|im_end|>",
"eos_token": "<|im_end|>",
"pad_token": "<|endoftext|>",
"unk_token": null
}
},
"createdAt": "2025-12-14T22:55:51.000Z",
"disabled": false,
"downloads": 58102,
"gated": false,
"id": "allenai/Molmo2-4B",
"lastModified": "2026-01-23T01:03:22.000Z",
"library_name": "transformers",
"likes": 54,
"model-index": null,
"modelId": "allenai/Molmo2-4B",
"pipeline_tag": "image-text-to-text",
"private": false,
"safetensors": {
"parameters": {
"F32": 4850869200
},
"total": 4850869200
},
"sha": "042abfa7a38879a376cec03d949eff0aefaa0600",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "README.md"
},
{
"rfilename": "added_tokens.json"
},
{
"rfilename": "chat_template.jinja"
},
{
"rfilename": "config.json"
},
{
"rfilename": "configuration_molmo2.py"
},
{
"rfilename": "generation_config.json"
},
{
"rfilename": "image_processing_molmo2.py"
},
{
"rfilename": "merges.txt"
},
{
"rfilename": "model-00001-of-00004.safetensors"
},
{
"rfilename": "model-00002-of-00004.safetensors"
},
{
"rfilename": "model-00003-of-00004.safetensors"
},
{
"rfilename": "model-00004-of-00004.safetensors"
},
{
"rfilename": "model.safetensors.index.json"
},
{
"rfilename": "modeling_molmo2.py"
},
{
"rfilename": "molmo_2_logo_RGB.png"
},
{
"rfilename": "preprocessor_config.json"
},
{
"rfilename": "processing_molmo2.py"
},
{
"rfilename": "processor_config.json"
},
{
"rfilename": "special_tokens_map.json"
},
{
"rfilename": "tokenizer.json"
},
{
"rfilename": "tokenizer_config.json"
},
{
"rfilename": "video_preprocessor_config.json"
},
{
"rfilename": "video_processing_molmo2.py"
},
{
"rfilename": "vocab.json"
}
],
"spaces": [
"aquanode/gpu-vram-calculator"
],
"tags": [
"transformers",
"safetensors",
"molmo2",
"image-text-to-text",
"multimodal",
"olmo",
"molmo",
"conversational",
"custom_code",
"en",
"dataset:allenai/Molmo2-Cap",
"dataset:allenai/Molmo2-VideoCapQA",
"dataset:allenai/Molmo2-VideoSubtitleQA",
"dataset:allenai/Molmo2-AskModelAnything",
"dataset:allenai/Molmo2-VideoPoint",
"dataset:allenai/Molmo2-VideoTrack",
"dataset:allenai/Molmo2-MultiImageQA",
"dataset:allenai/Molmo2-SynMultiImageQA",
"dataset:allenai/Molmo2-MultiImagePoint",
"base_model:Qwen/Qwen3-4B-Instruct-2507",
"base_model:finetune:Qwen/Qwen3-4B-Instruct-2507",
"license:apache-2.0",
"region:us"
],
"transformersInfo": {
"auto_model": "AutoModelForImageTextToText",
"custom_class": "modeling_molmo2.Molmo2ForConditionalGeneration",
"pipeline_tag": "image-text-to-text"
},
"usedStorage": 19415051449,
"widgetData": [
{
"text": "Hi, what can you help me with?"
},
{
"text": "What is 84 * 3 / 2?"
},
{
"text": "Tell me an interesting fact about the universe!"
},
{
"text": "Explain quantum computing in simple terms."
}
]
} | — |
model
| allenai/Molmo2-4B zetlyn/models-hf · 2025-12-14 | author allenai downloads 58102 gated false licence apache-2.0 likes 54 task image-text-to-text | source |
quantisation
| mu2solutions/Molmo2-4B-GGUF zetlyn/models-gguf · 2026-09-28 | author mu2solutions base allenai/Molmo2-4B downloads 117 licence apache-2.0 likes 0 | source |