Models you can run yourself

A model, every quantisation somebody made of it, and what each one costs to run.

Behind2 sourcesupdated 2h agofresh within 24h

freeSign in8032 claims are newer than 30 days and need a subscription

3,060things
722named by two sources or more
28conflicts
2sources

Only one source knows: GGUF quantisations 2276 · Hugging Face models 62

Covers. Every GGUF repository created since 2026-08-23, and the base model behind each one. 2,684 of those bases are named; without a Hugging Face token the run is throttled off after roughly 600 to 750 of them, so the model side of the join is partial and the scope says so on its front page. Excludes. Ollama, whose library names no Hugging Face repository to join on. Benchmarks, which have no machine-readable source.
Compared · what is held against what, and from which column of each source
PropertyHugging Face modelsGGUF quantisations
LicencecardData.licensecardData.license

Everything else the sources say is shown side by side, and not compared.

source=zetlyn/models-gguf ✕kind=model ✕

EverythingQuantised, and openly licensedmodel 1568quantisation 8921

Found

none
ThingKindLicenceDownloadsDate

Nothing here.

Facets

Kind 10489 of 10489 claims

quantisation8921
model1568

Source 10489 of 10489 claims

zetlyn/models-gguf8921
zetlyn/models-hf1568

Licence 8092 of 10489 claims

apache-2.0899
mit182
llama3.118
gemma16
other146
agpl-3.020
apple-amlr4
bigcode-openrail-m2

Task 1343 of 10489 claims

text-generation792
image-text-to-text320
automatic-speech-recognition39
text-classification38
any-to-any19
text-to-speech18
text-to-image15
sentence-similarity13

Sources

Hugging Face models primary

The model itself: its licence, its task and how many people fetch it.

model · failing1568

GGUF quantisations high

Which quantisations exist, which is what decides whether it runs on the machine somebody has.

quantisation · current8921