Qwen3.5-27B-Claude-4.6-Opus-Distilled-MLX-4bit
mlx-community/Qwen3.5-27B-Claude-4.6-Opus-Distilled-MLX-4bit
Uncategorised · mlx
4-bit Open on Hugging Face
Parameters
27B
Weights (est.)
≈ 15.1 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.
Details
- Base model
- Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled (quantized)
- Vendor
- Jackrong
- Task
- Uncategorised
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 5.2K in the last 30 days · 223K all time · 248 likes
- Published
- 2026-03-04 · updated 2026-03-06 (8mo ago)
- Languages
- en, zh
- Tags
- qwen3_5, reasoning, distilled, qwen, qwen3.5, apple-silicon, chain-of-thought, claude-4.6-opus, mlx-community
Other MLX builds of Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Qwen3.5-27B-Claude-4.6-Opus-Distilled-MLX-4bit (this one) | 4-bit | ≈ 15.1 GB | 24 GB+ | 5.2K |
| Huihui-Qwen3.5-27B-Claude-4.6-Opus-abliterated-4bit | 4-bit | ≈ 16.1 GB | 24 GB+ | 2.6K |
| Qwen3.5-27B-Claude-4.6-Opus-Distilled-MLX-6bit | 6-bit | ≈ 21.9 GB | 32 GB+ | 414 |
| Huihui-Qwen3.5-27B-Claude-4.6-Opus-abliterated-6bit | 6-bit | ≈ 22.8 GB | 32 GB+ | 154 |