MLX Community · First MLX build 4 Mar 2026
Qwen3.5-27B-Claude-4.6-Opus-Distilled
MLX
apache-2.0
A 27B parameter model, with 2 MLX builds, from 4-bit to 6-bit.
- Parameters
- 27B From Hugging Face
- Quantisation
- 4-bit Qwen3.5-27B-Claude-4.6-Opus-Distilled-MLX-4bit
- Memory needed
- 19 GB Estimate, unified memory
- Download
- 15.1 GB Weights, estimated
- Downloads
- 5.2K This build, last 30 days
- Task
- —
- MLX builds
- 2 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 19 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 · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/Qwen3.5-27B-Claude-4.6-Opus-Distilled-MLX-4bitMLX builds
2 on mlx-community| Qwen3.5-27B-Claude-4.6-Opus-Distilled-MLX-4bit | 4-bit | 15.1 GB | 19 GB | 5.2K |
|---|---|---|---|---|
| Qwen3.5-27B-Claude-4.6-Opus-Distilled-MLX-6bit | 6-bit | 21.9 GB | 27 GB | 425 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.