huihui-ai · First MLX build 25 Sept 2025
Huihui-gemma-3n-E4B-it-abliterated
MLX
Text gemma
A 6.9B parameter text generation model from huihui-ai, with 3 MLX builds, from 4-bit to 8-bit.
- Parameters
- 6.9B From Hugging Face
- Quantisation
- 8-bit Huihui-gemma-3n-E4B-it-abliterated-lm-8bit
- Memory needed
- 11 GB Estimate, unified memory
- Download
- 7.3 GB Weights, estimated
- Downloads
- 139 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 3 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/Huihui-gemma-3n-E4B-it-abliterated-lm-8bit --prompt "Hello"MLX builds
3 on mlx-community| Huihui-gemma-3n-E4B-it-abliterated-lm-4bit | 4-bit | 3.9 GB | 7 GB | 84 |
|---|---|---|---|---|
| Huihui-gemma-3n-E4B-it-abliterated-lm-6bit | 6-bit | 5.6 GB | 9 GB | 47 |
| Huihui-gemma-3n-E4B-it-abliterated-lm-8bit | 8-bit | 7.3 GB | 11 GB | 139 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.