gemma-4-E2B-it-MLX-4bit safetensors download | Hugging Bay

Q: What is this model?

AtomicChat/gemma-4-E2B-it-MLX-4bit is an open-weights language model for text generation published by AtomicChat, added to Hugging Bay Sep 19, 2026. Model from Hugging Face for text generation: AtomicChat/gemma-4-E2B-it-MLX-4bit · mlx

Q: Can I use it commercially?

It is released under the apache-2.0 license. Commercial use is allowed. Permissive open license: commercial use, modification, and redistribution are permitted.

Q: How big is it?

AtomicChat/gemma-4-E2B-it-MLX-4bit has 2B parameters. Hosted here: at least 7 listed files; full count and size unknown. Full repo upstream: 3.58 GB. The recommended download, model.safetensors, is 3.55 GB.

Q: What can I download here?

Hosted here: at least 7 listed files; full count and size unknown. Full repo upstream: 3.58 GB. The original release is at https://huggingface.co/AtomicChat/gemma-4-E2B-it-MLX-4bit.

Q: File pattern scans

Automated file-pattern scans flagged nothing; not a safety guarantee. 7 hosted files carry a published SHA-256 you can re-hash. The machine-readable verdict is at /api/artifacts/hf-model-atomicchat-gemma-4-e2b-it-mlx-4bit/safety on Hugging Bay.

Q: Will AtomicChat/gemma-4-E2B-it-MLX-4bit run on my computer?

We can’t check the fit; we don’t know your machine. We don’t have your machine’s specs, so no check ran and no verdict is shown. Answer two quick questions and we’ll estimate, from the memory you tell us, whether it fits your machine. Or skip it; you can still download; fit isn’t checked.

AtomicChat

gemma-4-E2B-it-MLX-4bit

Try browser chat with a small demo model (a separate model; device support is checked before loading).

AtomicChat/gemma-4-E2B-it-MLX-4bit

Model details

text generationLicense: apache-2.0SHA-256 recorded for 8 of 14 filessafetensors

Content controls: not assessed.

The catalog lists this model for having conversations. Catalog sources: license, cardMetadata.license, tags, task, cardMetadata.pipelineTag.

View as JSON →

Your next step

Use it from code

This Python snippet downloads the selected file. Running the model needs its own library and setup.

from urllib.request import urlretrieve

urlretrieve(
    "https://huggingbay.xyz/api/downloads/hf-model-atomicchat-gemma-4-e2b-it-mlx-4bit/model.safetensors",
    "model.safetensors",
)

Other ways

This file cannot open in the app. The app supports one GGUF file at a time.

See app requirements

7 hosted of 14 listed · Hashes recorded. Date not recorded.

Selected downloadmodel.safetensors3.55 GB · 1 file Download · 3.55 GB (1 file)

Open-file help

Content controls: not assessed.

Check your download →

Compare your file’s SHA-256 with the recorded hash.

7 hosted of 14 listed

Hashes recorded. Date not recorded.

File	大小	SHA-256	来源	下载
Weights
`model.safetensors` Default	3.55 GB	`ae5f08b1…9af9b73f` `ae5f08b10196a48dd8f495a3809055557b6ca6ff6c070d0f92d34b189af9b73f`	Hosted	下载
Tokenizer & config
`config.json`	6.39 KB	`6397cb6e…f6f9246c` `6397cb6eca41b911d1dcab74e17941351057bd759284052a2331918ff6f9246c`	Hosted	下载
`generation_config.json`	208 bytes	`d4226bbe…83ac03de` `d4226bbe3117d2d253ba4609720ba82c6c4ce4627a9a6ae05387c78983ac03de`	Hosted	下载
`hero.png`	185.7 KB	`9c0e503f…a1e71001` `9c0e503f4be60479a64510afec10878d3c2787e834b1dc9f89d3b900a1e71001`	Upstream only	File metadata
`model.safetensors.index.json`	218.3 KB	—	Upstream only	File metadata
`pill_atomic_v3.png`	23.4 KB	—	Upstream only	File metadata
`pill_discord_v3.png`	24.2 KB	—	Upstream only	File metadata
`pill_github_v3.png`	19.5 KB	—	Upstream only	File metadata
`chat_template.jinja`	18.6 KB	`0a2c8073…3f01c5b5` `0a2c8073c878ab1da004bee933a998606537bbb62016310352c7285c3f01c5b5`	Hosted	下载
`processor_config.json`	1.34 KB	`daf59741…a1693fd2` `daf597419c03cb3f20ac4f894cef7e4ab4a56dd07fef5131aa82ceffa1693fd2`	Hosted	下载
`tokenizer.json`	32.2 MB	`cc8d3a0c…627bfe0f` `cc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f`	Hosted	下载
`tokenizer_config.json`	3.73 KB	`ae79d534…34dfa6ae` `ae79d5349f543e549ca2721755b030dbba92614e25585f4c7e9aaa3734dfa6ae`	Hosted	下载
Docs
`.gitattributes`	1.61 KB	—	Upstream only	File metadata
`README.md`	4.68 KB	—	Upstream only	File metadata

检查下载文件

In the folder where you saved model.safetensors, run:

macOS

shasum -a 256 -- 'model.safetensors'

Linux

sha256sum -- 'model.safetensors'

Windows

Get-FileHash -LiteralPath 'model.safetensors' -Algorithm SHA256

Compare the result with the recorded SHA-256.

gemma-4-E2B-it-MLX-4bit

检查下载文件

Cookies