MLX Community · First MLX build 16 Jun 2026
gemma-4-E4B-it-CEVRL
MLX
Text
A 7.5B parameter text generation model, with 2 MLX builds at 8-bit.
- Parameters
- 7.5B From Hugging Face
- Quantisation
- 8-bit gemma-4-E4B-it-CEVRL-8bit
- Memory needed
- 11 GB Estimate, unified memory
- Download
- 7.9 GB Weights, estimated
- Downloads
- 33 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 2 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 11 GB at 8-bit
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · mlx-lm$ pip install -U mlx-lm
$ mlx_lm.generate --model mlx-community/gemma-4-E4B-it-CEVRL-8bit --prompt "Hello"MLX builds
2 on mlx-community| gemma-4-E4B-it-CEVRL-8bit | 8-bit | 7.9 GB | 11 GB | 33 |
|---|---|---|---|---|
| gemma-4-E4B-it-CEVRL | Unstated | 14.9 GB | 19 GB | 29 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.