MLX Community · First MLX build 14 Dec 2025
Qwen3-8B-abliterated-v2
MLX
Text apache-2.0
A 8.2B parameter text generation model, with one MLX build at MXFP4.
- Parameters
- 8.2B From Hugging Face
- Quantisation
- MXFP4 Qwen3-8B-abliterated-v2-mxfp4
- Memory needed
- 8 GB Estimate, unified memory
- Download
- 4.6 GB Weights, estimated
- Downloads
- 694 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 1 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 8 GB at MXFP4
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/Qwen3-8B-abliterated-v2-mxfp4 --prompt "Hello"MLX builds
1 on mlx-community| Qwen3-8B-abliterated-v2-mxfp4 | MXFP4 | 4.6 GB | 8 GB | 694 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.