ThinkingCap-Qwen3.6-27B-mlx-6Bit
mlx-community/ThinkingCap-Qwen3.6-27B-mlx-6Bit
Vision + text · transformers
6-bit Open on Hugging Face
Parameters
27B
Weights (est.)
≈ 21.9 GB
Mac memory (est.)
32 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-vlm on an Apple silicon Mac:
pip install mlx-vlmpython -m mlx_vlm.generate --model mlx-community/ThinkingCap-Qwen3.6-27B-mlx-6Bit --image photo.jpg --prompt "Describe this image"
Details
- Base model
- bottlecapai/ThinkingCap-Qwen3.6-27B (finetune)
- Vendor
- bottlecapai
- Task
- Vision + text
- Quantisation
- 6-bit
- Licence
- apache-2.0
- Downloads
- 166 in the last 30 days · 4.8K all time · 7 likes
- Published
- 2026-07-17 · updated 2026-07-17 (3mo ago)
- Tags
- qwen3_5, qwen3_6, token-efficient, efficient-thinking, mlx-my-repo
Other MLX builds of bottlecapai/ThinkingCap-Qwen3.6-27B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| ThinkingCap-Qwen3.6-27B-OptiQ-4bit | 4-bit | ≈ 16.1 GB | 24 GB+ | 357 |
| ThinkingCap-Qwen3.6-27B-mlx-6Bit (this one) | 6-bit | ≈ 21.9 GB | 32 GB+ | 166 |