Huihui-Qwen3.5-35B-A3B-abliterated-mxfp4
mlx-community/Huihui-Qwen3.5-35B-A3B-abliterated-mxfp4
Text generation · mlx
MXFP4 Open on Hugging Face
Parameters
35B
Weights (est.)
≈ 19.5 GB
Mac memory (est.)
24 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/Huihui-Qwen3.5-35B-A3B-abliterated-mxfp4 --prompt "Hello"
Details
- Base model
- huihui-ai/Huihui-Qwen3.5-35B-A3B-abliterated (quantized)
- Vendor
- huihui-ai
- Task
- Text generation
- Quantisation
- MXFP4
- Licence
- apache-2.0
- Downloads
- 200 in the last 30 days · 5.4K all time · 3 likes
- Published
- 2026-03-04 · updated 2026-03-04 (8mo ago)
- Tags
- qwen3_5_moe, abliterated, uncensored
Other MLX builds of huihui-ai/Huihui-Qwen3.5-35B-A3B-abliterated
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Huihui-Qwen3.5-35B-A3B-abliterated-mxfp4 (this one) | MXFP4 | ≈ 19.5 GB | 24 GB+ | 200 |
| Huihui-Qwen3.5-35B-A3B-abliterated-6bit | 6-bit | ≈ 28.2 GB | 48 GB+ | 315 |