Skip to content
Weights Not Walls
Menu

google

gemma-3-4b-pt

Reviewedgated on the Hubaccepts images
Size
4.3B parameterscounted from the safetensors header on the Hub
Licence
unknown, Gemma Terms of UseOur reading, check the licence: Commercial use is allowed with no user or revenue cap, but the Gemma Prohibited Use Policy (a separate document, not in this text) is part of the terms, and you must pass the use restrictions on as enforceable terms to anyone you distribute to. Models distilled from Gemma or trained on its outputs to perform like it count as Model Derivatives and stay under these terms, and Google may restrict use remotely if it believes the terms are broken. The page says these terms cover the models in its appendix (Gemma 1 to 3, 3n and variants) and that Gemma 4 has a separate licence.
On the Hub since
20 Feb 2025the date the repo was created
Context length
Not known
Kind
Base model (no base model declared on the Hub)Gemma3ForConditionalGeneration
On Hugging Face
google/gemma-3-4b-pt222k downloads in the last 30 days, 180 likes

Scores

No independent scores for this model in Epoch AI's data. A score is only shown here when Epoch's name for a model matches this repo with certainty; an uncertain match is left out rather than guessed.

Claimed by the maker Claimed

The model card has no claimed scores in a machine-readable form (the card's model-index), so none are shown. The maker may give scores in the card text: read the card.

Other views, which we link to and do not copy: look this model up on Artificial Analysis and the Arena leaderboard.

Run it yourself

file sizes read from the Hub 19 Nov 2026

Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 1.3 GB, a rough allowance by model size, because we do not have this model's attention config. Choose a machine above to see a verdict for each format. Method

GGUF for llama.cpp, Ollama, LM Studio and others

google/gemma-3-4b-pt-qat-q4_0-gguf (the maker's own conversion), 34 downloads. Sizes are the real files on the Hub, all parts added up. For image input you also need the projector file mmproj-model-f16-4B.gguf (0.79 GB), not counted below.

FormatSizeMemory neededGet it
Q4_02.9 GBfile size4.7 GB2.9 + 1.3 + 0.50
Commands
llama.cpp
llama-server -hf google/gemma-3-4b-pt-qat-q4_0-gguf:Q4_0
Ollama
ollama run hf.co/google/gemma-3-4b-pt-qat-q4_0-gguf:Q4_0
Download
hf download google/gemma-3-4b-pt-qat-q4_0-gguf --include "gemma-3-4b-pt-q4_0.gguf" --local-dir gemma-3-4b-pt-qat-q4_0-gguf

Original weights size from the safetensors header, for vLLM, SGLang, Transformers

FormatSizeMemory neededRepo
BF16original weights8.0 GBfile size9.8 GB8.0 + 1.3 + 0.50
hf download google/gemma-3-4b-pt --local-dir gemma-3-4b-pt
Other conversions (2; sizes not read)

The Hub tags 26 quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.

Run it by API

Hugging Face Inference Providers, fetched 19 Nov 2026, 13:58 UTC

No provider on Hugging Face Inference Providers serves this model (as of 19 Nov 2026, 13:58 UTC). Other hosts may; we only list what the router reports.

Not built yet: one key for every open model, with BlockRun, and our own tested-quality score per provider. Until then, precision and measured speed are the best guide to a provider here.

Fine-tunes of this model

from our snapshot of the Hub

Repos that declare this model as their base, most downloaded first. Listing is not a recommendation; unreviewed ones have not been checked.

Planned for this page Not built yet

Try it in private chat
A link to Solana AI's confidential chat for the models it serves. This model is not listed as served there.
Fine-tune it
Fine-tuning a few base models from this page and publishing the result here.
Creators and earnings
Pages for people who publish fine-tunes and adapters of this model, and what they earn.
Fund and bounties
Bounties for new open models, paid from a public fund. How the fund will work.
Contribute compute
How to give compute to open model work, with Akash.

Model data from the Hugging Face Hub 19 Nov 2026, 13:43 UTC. The repo. Found a mistake on this page? Tell us.