amd/Instella-MoE-16B-A3B-Think

hf amd/Instella-MoE-16B-A3B-Think 2 sources, 3 claims · Watch

What each source says

PropertySourceSaidMeans here
Author
author
not compared		GGUF quantisationsTULLUS
receipt
Source
GGUF quantisations
Its words
TULLUS
Read by
field:author
Said since
2026-09-28 11:46 UTC
Last answered
2026-10-02 18:04 UTC
Original
open at the source
What the source handed over
{
  "_id": "6ab161f13eec8726144dec4b",
  "author": "TULLUS",
  "cardData": {
    "base_model": "amd/Instella-MoE-16B-A3B-Think",
    "base_model_relation": "quantized",
    "language": [
      "en"
    ],
    "library_name": "gguf",
    "license": "other",
    "license_link": "https://huggingface.co/amd/Instella-MoE-16B-A3B-Think/blob/main/LICENSE",
    "license_name": "researchrail",
    "pipeline_tag": "text-generation",
    "tags": [
      "instella",
      "moe",
      "amd",
      "rocm",
      "gguf",
      "llama.cpp",
      "reasoning",
      "gfx1201"
    ]
  },
  "createdAt": "2026-09-21T16:57:21.000Z",
  "downloads": 373,
  "gated": false,
  "id": "TULLUS/Instella-MoE-16B-A3B-Think-GGUF",
  "lastModified": "2026-09-25T03:09:12.000Z",
  "library_name": "gguf",
  "likes": 0,
  "modelId": "TULLUS/Instella-MoE-16B-A3B-Think-GGUF",
  "pipeline_tag": "text-generation",
  "private": false,
  "sha": "0645a49719e108968b31c8e431f283c9f43c4933",
  "siblings": [
    {
      "rfilename": ".gitattributes"
    },
    {
      "rfilename": "Instella-MoE-16B-A3B-Think-F16.gguf"
    },
    {
      "rfilename": "Instella-MoE-16B-A3B-Think-Q4_K_M.gguf"
    },
    {
      "rfilename": "Instella-MoE-16B-A3B-Think-Q5_K_M.gguf"
    },
    {
      "rfilename": "Instella-MoE-16B-A3B-Think-Q6_K.gguf"
    },
    {
      "rfilename": "Instella-MoE-16B-A3B-Think-i1-Q4_K_S.gguf"
    },
    {
      "rfilename": "README.md"
    }
  ],
  "tags": [
    "gguf",
    "instella",
    "moe",
    "amd",
    "rocm",
    "llama.cpp",
    "reasoning",
    "gfx1201",
    "text-generation",
    "en",
    "arxiv:2609.00791",
    "base_model:amd/Instella-MoE-16B-A3B-Think",
    "base_model:quantized:amd/Instella-MoE-16B-A3B-Think",
    "license:other",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ]
}
—
Author
author
not compared		Hugging Face modelsamd
receipt
Source
Hugging Face models
Original
open at the source

This source has not kept a receipt for this claim yet. The next update that reads it will.

—
Base
base
GGUF quantisationsamd/Instella-MoE-16B-A3B-Think
receipt
Source
GGUF quantisations
Its words
amd/Instella-MoE-16B-A3B-Think
Read by
field:cardData.base_model[]
Said since
2026-09-28 11:46 UTC
Last answered
2026-10-02 18:04 UTC
Original
open at the source
What the source handed over
{
  "_id": "6ab161f13eec8726144dec4b",
  "author": "TULLUS",
  "cardData": {
    "base_model": "amd/Instella-MoE-16B-A3B-Think",
    "base_model_relation": "quantized",
    "language": [
      "en"
    ],
    "library_name": "gguf",
    "license": "other",
    "license_link": "https://huggingface.co/amd/Instella-MoE-16B-A3B-Think/blob/main/LICENSE",
    "license_name": "researchrail",
    "pipeline_tag": "text-generation",
    "tags": [
      "instella",
      "moe",
      "amd",
      "rocm",
      "gguf",
      "llama.cpp",
      "reasoning",
      "gfx1201"
    ]
  },
  "createdAt": "2026-09-21T16:57:21.000Z",
  "downloads": 373,
  "gated": false,
  "id": "TULLUS/Instella-MoE-16B-A3B-Think-GGUF",
  "lastModified": "2026-09-25T03:09:12.000Z",
  "library_name": "gguf",
  "likes": 0,
  "modelId": "TULLUS/Instella-MoE-16B-A3B-Think-GGUF",
  "pipeline_tag": "text-generation",
  "private": false,
  "sha": "0645a49719e108968b31c8e431f283c9f43c4933",
  "siblings": [
    {
      "rfilename": ".gitattributes"
    },
    {
      "rfilename": "Instella-MoE-16B-A3B-Think-F16.gguf"
    },
    {
      "rfilename": "Instella-MoE-16B-A3B-Think-Q4_K_M.gguf"
    },
    {
      "rfilename": "Instella-MoE-16B-A3B-Think-Q5_K_M.gguf"
    },
    {
      "rfilename": "Instella-MoE-16B-A3B-Think-Q6_K.gguf"
    },
    {
      "rfilename": "Instella-MoE-16B-A3B-Think-i1-Q4_K_S.gguf"
    },
    {
      "rfilename": "README.md"
    }
  ],
  "tags": [
    "gguf",
    "instella",
    "moe",
    "amd",
    "rocm",
    "llama.cpp",
    "reasoning",
    "gfx1201",
    "text-generation",
    "en",
    "arxiv:2609.00791",
    "base_model:amd/Instella-MoE-16B-A3B-Think",
    "base_model:quantized:amd/Instella-MoE-16B-A3B-Think",
    "license:other",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ]
}
—
Downloads
downloads
not compared		GGUF quantisations373
receipt
Source
GGUF quantisations
Its words
373
Read by
field:downloads
Said since
2026-09-28 11:46 UTC
Last answered
2026-10-02 18:04 UTC
Original
open at the source
What the source handed over
{
  "_id": "6ab161f13eec8726144dec4b",
  "author": "TULLUS",
  "cardData": {
    "base_model": "amd/Instella-MoE-16B-A3B-Think",
    "base_model_relation": "quantized",
    "language": [
      "en"
    ],
    "library_name": "gguf",
    "license": "other",
    "license_link": "https://huggingface.co/amd/Instella-MoE-16B-A3B-Think/blob/main/LICENSE",
    "license_name": "researchrail",
    "pipeline_tag": "text-generation",
    "tags": [
      "instella",
      "moe",
      "amd",
      "rocm",
      "gguf",
      "llama.cpp",
      "reasoning",
      "gfx1201"
    ]
  },
  "createdAt": "2026-09-21T16:57:21.000Z",
  "downloads": 373,
  "gated": false,
  "id": "TULLUS/Instella-MoE-16B-A3B-Think-GGUF",
  "lastModified": "2026-09-25T03:09:12.000Z",
  "library_name": "gguf",
  "likes": 0,
  "modelId": "TULLUS/Instella-MoE-16B-A3B-Think-GGUF",
  "pipeline_tag": "text-generation",
  "private": false,
  "sha": "0645a49719e108968b31c8e431f283c9f43c4933",
  "siblings": [
    {
      "rfilename": ".gitattributes"
    },
    {
      "rfilename": "Instella-MoE-16B-A3B-Think-F16.gguf"
    },
    {
      "rfilename": "Instella-MoE-16B-A3B-Think-Q4_K_M.gguf"
    },
    {
      "rfilename": "Instella-MoE-16B-A3B-Think-Q5_K_M.gguf"
    },
    {
      "rfilename": "Instella-MoE-16B-A3B-Think-Q6_K.gguf"
    },
    {
      "rfilename": "Instella-MoE-16B-A3B-Think-i1-Q4_K_S.gguf"
    },
    {
      "rfilename": "README.md"
    }
  ],
  "tags": [
    "gguf",
    "instella",
    "moe",
    "amd",
    "rocm",
    "llama.cpp",
    "reasoning",
    "gfx1201",
    "text-generation",
    "en",
    "arxiv:2609.00791",
    "base_model:amd/Instella-MoE-16B-A3B-Think",
    "base_model:quantized:amd/Instella-MoE-16B-A3B-Think",
    "license:other",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ]
}
—
Downloads
downloads
not compared		Hugging Face models2920
receipt
Source
Hugging Face models
Its words
2920
Read by
field:downloads
Said since
2026-10-02 12:02 UTC
Original
open at the source
What the source handed over
{
  "_asked": "amd/Instella-MoE-16B-A3B-Think",
  "_id": "6a627b51ec66e8f7980d6737",
  "author": "amd",
  "cardData": {
    "language": [
      "en"
    ],
    "library_name": "transformers",
    "license": "other",
    "license_link": "LICENSE",
    "license_name": "researchrail",
    "pipeline_tag": "text-generation",
    "tags": [
      "instella",
      "moe",
      "amd",
      "rocm"
    ]
  },
  "config": {
    "architectures": [
      "InstellaMoEForCausalLM"
    ],
    "auto_map": {
      "AutoConfig": "configuration_instella_moe.InstellaMoEConfig",
      "AutoModel": "modeling_instella_moe.InstellaMoEModel",
      "AutoModelForCausalLM": "modeling_instella_moe.InstellaMoEForCausalLM"
    },
    "model_type": "deepseek_v3",
    "num_experts_per_tok": 6,
    "tokenizer_config": {
      "bos_token": {
        "__type": "AddedToken",
        "content": "<｜begin▁of▁sentence｜>",
        "lstrip": false,
        "normalized": true,
        "rstrip": false,
        "single_word": false
      },
      "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='', is_first_sp=true) %}{%- for message in messages %}{%- if message['role'] == 'system' %}{%- if ns.is_first_sp %}{% set ns.system_prompt = ns.system_prompt + message['content'] %}{% set ns.is_first_sp = false %}{%- else %}{% set ns.system_prompt = ns.system_prompt + '\n\n' + message['content'] %}{%- endif %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{{'<｜Assistant｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}",
      "eos_token": {
        "__type": "AddedToken",
        "content": "<｜end▁of▁sentence｜>",
        "lstrip": false,
        "normalized": true,
        "rstrip": false,
        "single_word": false
      },
      "pad_token": {
        "__type": "AddedToken",
        "content": "<｜end▁of▁sentence｜>",
        "lstrip": false,
        "normalized": true,
        "rstrip": false,
        "single_word": false
      },
      "unk_token": null
    }
  },
  "createdAt": "2026-07-23T20:36:33.000Z",
  "disabled": false,
  "downloads": 2920,
  "gated": false,
  "id": "amd/Instella-MoE-16B-A3B-Think",
  "lastModified": "2026-09-02T14:16:10.000Z",
  "library_name": "transformers",
  "likes": 181,
  "model-index": null,
  "modelId": "amd/Instella-MoE-16B-A3B-Think",
  "pipeline_tag": "text-generation",
  "private": false,
  "safetensors": {
    "parameters": {
      "BF16": 15862787584,
      "F32": 1664
    },
    "total": 15862789248
  },
  "sha": "74d28c1a8425583d7805b58e2caa9c13d6b62929",
  "siblings": [
    {
      "rfilename": ".gitattributes"
    },
    {
      "rfilename": "LICENSE"
    },
    {
      "rfilename": "README.md"
    },
    {
      "rfilename": "__init__.py"
    },
    {
      "rfilename": "_transformers_compat.py"
    },
    {
      "rfilename": "config.json"
    },
    {
      "rfilename": "configuration_instella_moe.py"
    },
    {
      "rfilename": "generation_config.json"
    },
    {
      "rfilename": "images/fig_cost_performance.png"
    },
    {
      "rfilename": "images/result_table_base_long.png"
    },
    {
      "rfilename": "images/result_table_base_standard.png"
    },
    {
      "rfilename": "images/result_table_instruct.png"
    },
    {
      "rfilename": "model-00001-of-00006.safetensors"
    },
    {
      "rfilename": "model-00002-of-00006.safetensors"
    },
    {
      "rfilename": "model-00003-of-00006.safetensors"
    },
    {
      "rfilename": "model-00004-of-00006.safetensors"
    },
    {
      "rfilename": "model-00005-of-00006.safetensors"
    },
    {
      "rfilename": "model-00006-of-00006.safetensors"
    },
    {
      "rfilename": "model.safetensors.index.json"
    },
    {
      "rfilename": "modeling_instella_moe.py"
    },
    {
      "rfilename": "special_tokens_map.json"
    },
    {
      "rfilename": "tokenizer.json"
    },
    {
      "rfilename": "tokenizer_config.json"
    }
  ],
  "spaces": [],
  "tags": [
    "transformers",
    "safetensors",
    "deepseek_v3",
    "text-generation",
    "instella",
    "moe",
    "amd",
    "rocm",
    "conversational",
    "custom_code",
    "en",
    "arxiv:2609.00791",
    "license:other",
    "text-generation-inference",
    "endpoints_compatible",
    "region:us"
  ],
  "transformersInfo": {
    "auto_model": "AutoModelForCausalLM",
    "custom_class": "modeling_instella_moe.InstellaMoEForCausalLM",
    "pipeline_tag": "text-generation",
    "processor": "AutoTokenizer"
  },
  "usedStorage": 31727183587,
  "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."
    }
  ]
}
—
Downloads
downloads
not compared		3138
receipt
Source
Hugging Face models
Original
open at the source

This source has not kept a receipt for this claim yet. The next update that reads it will.

—
Gated
gated
Hugging Face modelsfalse
receipt
Source
Hugging Face models
Original
open at the source

This source has not kept a receipt for this claim yet. The next update that reads it will.

—
Licence
licence
GGUF quantisationsother
receipt
Source
GGUF quantisations
Its words
other
Read by
field:cardData.license
Said since
2026-09-28 11:46 UTC
Last answered
2026-10-02 18:04 UTC
Original
open at the source
What the source handed over
{
  "_id": "6ab161f13eec8726144dec4b",
  "author": "TULLUS",
  "cardData": {
    "base_model": "amd/Instella-MoE-16B-A3B-Think",
    "base_model_relation": "quantized",
    "language": [
      "en"
    ],
    "library_name": "gguf",
    "license": "other",
    "license_link": "https://huggingface.co/amd/Instella-MoE-16B-A3B-Think/blob/main/LICENSE",
    "license_name": "researchrail",
    "pipeline_tag": "text-generation",
    "tags": [
      "instella",
      "moe",
      "amd",
      "rocm",
      "gguf",
      "llama.cpp",
      "reasoning",
      "gfx1201"
    ]
  },
  "createdAt": "2026-09-21T16:57:21.000Z",
  "downloads": 373,
  "gated": false,
  "id": "TULLUS/Instella-MoE-16B-A3B-Think-GGUF",
  "lastModified": "2026-09-25T03:09:12.000Z",
  "library_name": "gguf",
  "likes": 0,
  "modelId": "TULLUS/Instella-MoE-16B-A3B-Think-GGUF",
  "pipeline_tag": "text-generation",
  "private": false,
  "sha": "0645a49719e108968b31c8e431f283c9f43c4933",
  "siblings": [
    {
      "rfilename": ".gitattributes"
    },
    {
      "rfilename": "Instella-MoE-16B-A3B-Think-F16.gguf"
    },
    {
      "rfilename": "Instella-MoE-16B-A3B-Think-Q4_K_M.gguf"
    },
    {
      "rfilename": "Instella-MoE-16B-A3B-Think-Q5_K_M.gguf"
    },
    {
      "rfilename": "Instella-MoE-16B-A3B-Think-Q6_K.gguf"
    },
    {
      "rfilename": "Instella-MoE-16B-A3B-Think-i1-Q4_K_S.gguf"
    },
    {
      "rfilename": "README.md"
    }
  ],
  "tags": [
    "gguf",
    "instella",
    "moe",
    "amd",
    "rocm",
    "llama.cpp",
    "reasoning",
    "gfx1201",
    "text-generation",
    "en",
    "arxiv:2609.00791",
    "base_model:amd/Instella-MoE-16B-A3B-Think",
    "base_model:quantized:amd/Instella-MoE-16B-A3B-Think",
    "license:other",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ]
}
—
Licence
licence
Hugging Face modelsother
receipt
Source
Hugging Face models
Original
open at the source

This source has not kept a receipt for this claim yet. The next update that reads it will.

—
Likes
likes
not compared		GGUF quantisations0
receipt
Source
GGUF quantisations
Its words
0
Read by
field:likes
Said since
2026-09-28 11:46 UTC
Last answered
2026-10-02 18:04 UTC
Original
open at the source
What the source handed over
{
  "_id": "6ab161f13eec8726144dec4b",
  "author": "TULLUS",
  "cardData": {
    "base_model": "amd/Instella-MoE-16B-A3B-Think",
    "base_model_relation": "quantized",
    "language": [
      "en"
    ],
    "library_name": "gguf",
    "license": "other",
    "license_link": "https://huggingface.co/amd/Instella-MoE-16B-A3B-Think/blob/main/LICENSE",
    "license_name": "researchrail",
    "pipeline_tag": "text-generation",
    "tags": [
      "instella",
      "moe",
      "amd",
      "rocm",
      "gguf",
      "llama.cpp",
      "reasoning",
      "gfx1201"
    ]
  },
  "createdAt": "2026-09-21T16:57:21.000Z",
  "downloads": 373,
  "gated": false,
  "id": "TULLUS/Instella-MoE-16B-A3B-Think-GGUF",
  "lastModified": "2026-09-25T03:09:12.000Z",
  "library_name": "gguf",
  "likes": 0,
  "modelId": "TULLUS/Instella-MoE-16B-A3B-Think-GGUF",
  "pipeline_tag": "text-generation",
  "private": false,
  "sha": "0645a49719e108968b31c8e431f283c9f43c4933",
  "siblings": [
    {
      "rfilename": ".gitattributes"
    },
    {
      "rfilename": "Instella-MoE-16B-A3B-Think-F16.gguf"
    },
    {
      "rfilename": "Instella-MoE-16B-A3B-Think-Q4_K_M.gguf"
    },
    {
      "rfilename": "Instella-MoE-16B-A3B-Think-Q5_K_M.gguf"
    },
    {
      "rfilename": "Instella-MoE-16B-A3B-Think-Q6_K.gguf"
    },
    {
      "rfilename": "Instella-MoE-16B-A3B-Think-i1-Q4_K_S.gguf"
    },
    {
      "rfilename": "README.md"
    }
  ],
  "tags": [
    "gguf",
    "instella",
    "moe",
    "amd",
    "rocm",
    "llama.cpp",
    "reasoning",
    "gfx1201",
    "text-generation",
    "en",
    "arxiv:2609.00791",
    "base_model:amd/Instella-MoE-16B-A3B-Think",
    "base_model:quantized:amd/Instella-MoE-16B-A3B-Think",
    "license:other",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ]
}
—
Likes
likes
not compared		Hugging Face models181
receipt
Source
Hugging Face models
Original
open at the source

This source has not kept a receipt for this claim yet. The next update that reads it will.

—
Task
task
Hugging Face modelstext-generation
receipt
Source
Hugging Face models
Original
open at the source

This source has not kept a receipt for this claim yet. The next update that reads it will.

—

model

amd/Instella-MoE-16B-A3B-Think
zetlyn/models-hf · 2026-07-23
author amd downloads 3138 gated false licence other likes 181 task text-generation source
amd/Instella-MoE-16B-A3B-Think
zetlyn/models-hf · 2026-07-23
author amd downloads 2920 gated false licence other likes 181 task text-generation source

quantisation

TULLUS/Instella-MoE-16B-A3B-Think-GGUF
zetlyn/models-gguf · 2026-09-21
author TULLUS base amd/Instella-MoE-16B-A3B-Think downloads 373 licence other likes 0 source