Skip to content
Weights Not Walls
Menu

google

gemma-4-E4B

Reviewed

Runs on your machine

Choose a machine

We then show the largest format that fits, from real file sizes where we have them.

All formats

How good

No independent scores yet

Nothing in Epoch AI's data matches this repo with certainty.

Scores

Run by API

Not served

No provider on Hugging Face Inference Providers serves it.

Details

Licence

Permissive

Apache License 2.0

Our reading

Size and context

8.0B

parameters
128k tokens of context

Sources

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: 0.25 GB, worked out from the model's config (google/gemma-4-E4B), at 16-bit precision. Choose a machine above to see a verdict for each format. Method

weights context cache runtime

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

mradermacher/gemma-4-E4B-GGUF (converted by mradermacher), 4.6k downloads. Sizes are the real files on the Hub, all parts added up. Showing the common levels.

FormatSizeMemory neededMemoryGet it
Q4_K_M5.0 GBfile size5.7 GB5.0 + 0.25 + 0.50
Commands
llama.cpp
llama-server -hf mradermacher/gemma-4-E4B-GGUF:Q4_K_M
Ollama
ollama run hf.co/mradermacher/gemma-4-E4B-GGUF:Q4_K_M
Download
hf download mradermacher/gemma-4-E4B-GGUF --include "gemma-4-E4B.Q4_K_M.gguf" --local-dir gemma-4-E4B-GGUF
Q5_K_M5.4 GBfile size6.1 GB5.4 + 0.25 + 0.50
Commands
llama.cpp
llama-server -hf mradermacher/gemma-4-E4B-GGUF:Q5_K_M
Ollama
ollama run hf.co/mradermacher/gemma-4-E4B-GGUF:Q5_K_M
Download
hf download mradermacher/gemma-4-E4B-GGUF --include "gemma-4-E4B.Q5_K_M.gguf" --local-dir gemma-4-E4B-GGUF
Q6_K5.8 GBfile size6.5 GB5.8 + 0.25 + 0.50
Commands
llama.cpp
llama-server -hf mradermacher/gemma-4-E4B-GGUF:Q6_K
Ollama
ollama run hf.co/mradermacher/gemma-4-E4B-GGUF:Q6_K
Download
hf download mradermacher/gemma-4-E4B-GGUF --include "gemma-4-E4B.Q6_K.gguf" --local-dir gemma-4-E4B-GGUF
Q8_07.5 GBfile size8.2 GB7.5 + 0.25 + 0.50
Commands
llama.cpp
llama-server -hf mradermacher/gemma-4-E4B-GGUF:Q8_0
Ollama
ollama run hf.co/mradermacher/gemma-4-E4B-GGUF:Q8_0
Download
hf download mradermacher/gemma-4-E4B-GGUF --include "gemma-4-E4B.Q8_0.gguf" --local-dir gemma-4-E4B-GGUF

MLX for Apple silicon

FormatSizeMemory neededMemoryRepo
MLX 4bitkinguniverse129/gemma-4-E4B-4bit3.9 GBfile size4.7 GB3.9 + 0.25 + 0.50Download page
MLX 4bitSiarhei/gemma-4-E4B-4bit3.9 GBfile size4.7 GB3.9 + 0.25 + 0.50Download page

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

FormatSizeMemory neededMemoryRepo
BF16original weights14.9 GBfile size15.6 GB14.9 + 0.25 + 0.50
hf download google/gemma-4-E4B --local-dir gemma-4-E4B

The Hub tags 38 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, 15:15 UTC. The repo. Found a mistake on this page? Tell us.