mlabonne · First MLX build 22 Mar 2025
gemma-3-4b-it-abliterated
MLX
Text gemma
A 4.6B parameter text generation model from mlabonne, with 4 MLX builds, from 4-bit to bf16.
- Parameters
- 4.6B From Hugging Face
- Quantisation
- 4-bit gemma-3-4b-it-abliterated-4bit-text
- Memory needed
- 5 GB Estimate, unified memory
- Download
- 2.6 GB Weights, estimated
- Downloads
- 112 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 4 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 5 GB at 4-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-3-4b-it-abliterated-4bit-text --prompt "Hello"MLX builds
4 on mlx-community| gemma-3-4b-it-abliterated-4bit-text | 4-bit | 2.6 GB | 5 GB | 112 |
|---|---|---|---|---|
| gemma-3-4b-it-abliterated-6bit-text | 6-bit | 3.7 GB | 7 GB | 82 |
| gemma-3-4b-it-abliterated-8bit-text | 8-bit | 4.8 GB | 8 GB | 60 |
| gemma-3-4b-it-abliterated-bf16-text | bf16 | 9.1 GB | 13 GB | 51 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.