google · fine-tune of google/gemma-4-E2B
gemma-4-E2B-it
Runs on your machine
Choose a machine
We then show the largest format that fits, from real file sizes where we have them.
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
Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 0.12 GB, worked out from the model's config (google/gemma-4-E2B-it), 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
unsloth/gemma-4-E2B-it-GGUF (converted by unsloth), 814k downloads. Sizes are the real files on the Hub, all parts added up. Showing the common levels.
| Format | Size | Memory needed | Memory | Get it |
|---|---|---|---|---|
| Q4_K_M | 2.9 GBfile size | 3.5 GB2.9 + 0.12 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/gemma-4-E2B-it-GGUF:Q4_K_MOllama ollama run hf.co/unsloth/gemma-4-E2B-it-GGUF:Q4_K_MDownload hf download unsloth/gemma-4-E2B-it-GGUF --include "gemma-4-E2B-it-Q4_K_M.gguf" --local-dir gemma-4-E2B-it-GGUF | |
| Q5_K_M | 3.1 GBfile size | 3.7 GB3.1 + 0.12 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/gemma-4-E2B-it-GGUF:Q5_K_MOllama ollama run hf.co/unsloth/gemma-4-E2B-it-GGUF:Q5_K_MDownload hf download unsloth/gemma-4-E2B-it-GGUF --include "gemma-4-E2B-it-Q5_K_M.gguf" --local-dir gemma-4-E2B-it-GGUF | |
| Q6_K | 4.2 GBfile size | 4.8 GB4.2 + 0.12 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/gemma-4-E2B-it-GGUF:Q6_KOllama ollama run hf.co/unsloth/gemma-4-E2B-it-GGUF:Q6_KDownload hf download unsloth/gemma-4-E2B-it-GGUF --include "gemma-4-E2B-it-Q6_K.gguf" --local-dir gemma-4-E2B-it-GGUF | |
| Q8_0 | 4.7 GBfile size | 5.3 GB4.7 + 0.12 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/gemma-4-E2B-it-GGUF:Q8_0Ollama ollama run hf.co/unsloth/gemma-4-E2B-it-GGUF:Q8_0Download hf download unsloth/gemma-4-E2B-it-GGUF --include "gemma-4-E2B-it-Q8_0.gguf" --local-dir gemma-4-E2B-it-GGUF | |
| BF16 | 8.7 GBfile size | 9.3 GB8.7 + 0.12 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/gemma-4-E2B-it-GGUF:BF16Ollama ollama run hf.co/unsloth/gemma-4-E2B-it-GGUF:BF16Download hf download unsloth/gemma-4-E2B-it-GGUF --include "gemma-4-E2B-it-BF16.gguf" --local-dir gemma-4-E2B-it-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Memory | Repo |
|---|---|---|---|---|
| MLX 4bitlmstudio-community/gemma-4-E2B-it-MLX-4bit | 4.0 GBfile size | 4.7 GB4.0 + 0.12 + 0.50 | Download page | |
| MLX 8bitlmstudio-community/gemma-4-E2B-it-MLX-8bit | 5.5 GBfile size | 6.1 GB5.5 + 0.12 + 0.50 | Download page |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Memory | Repo |
|---|---|---|---|---|
| BF16original weights | 9.5 GBfile size | 10.2 GB9.5 + 0.12 + 0.50 |
hf download google/gemma-4-E2B-it --local-dir gemma-4-E2B-itOther conversions (8; sizes not read)
- google/gemma-4-E2B-it-qat-q4_0-unquantized Other, by the maker, 10k downloads
- unsloth/gemma-4-E2B-it-unsloth-bnb-4bit bitsandbytes, 4bit, 79k downloads
- cyankiwi/gemma-4-E2B-it-AWQ-INT4 AWQ, int4, 25k downloads
- onnx-community/gemma-4-E2B-it-ONNX Other, 7.1k downloads
- mlc-ai/gemma-4-E2B-it-q4f16_1-MLC Other, 2.1k downloads
- Vishva007/gemma-4-E2B-it-W4A16-AutoRound-GPTQ GPTQ, w4a16, 1.9k downloads
- unsloth/gemma-4-E2B-it-NVFP4 NVFP4, 877 downloads
- OpenVINO/gemma-4-E2B-it-int4-ov Other, int4, 859 downloads
The Hub tags 100 or more quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.
Run it by API
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
- unsloth/gemma-4-E2B-it5.1B65kUnreviewed
- google/gemma-4-E2B-it-qat-mobile-transformers3.7kUnreviewed
- Cactus-Compute/gemma-4-e2b-it-hybrid4.6B271Unreviewed
- Cactus-Compute/gemma-4-E2B-it165Unreviewed
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.