huihui-ai · First MLX build 4 Mar 2026
Huihui-Qwen3.5-35B-A3B-abliterated
MLX
Text apache-2.0
A 35B parameter text generation model from huihui-ai, with 2 MLX builds, from MXFP4 to 6-bit.
- Parameters
- 35B From Hugging Face
- Quantisation
- 6-bit Huihui-Qwen3.5-35B-A3B-abliterated-6bit
- Memory needed
- 34 GB Estimate, unified memory
- Download
- 28.2 GB Weights, estimated
- Downloads
- 319 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 34 GB at 6-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-Qwen3.5-35B-A3B-abliterated-6bit --prompt "Hello"MLX builds
2 on mlx-community| Huihui-Qwen3.5-35B-A3B-abliterated-mxfp4 | MXFP4 | 19.5 GB | 24 GB | 205 |
|---|---|---|---|---|
| Huihui-Qwen3.5-35B-A3B-abliterated-6bit | 6-bit | 28.2 GB | 34 GB | 319 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.