ThinkingCap-Qwen3.6-27B-OptiQ-4bit
mlx-community/ThinkingCap-Qwen3.6-27B-OptiQ-4bit
Vision + text · mlx
4-bit Open on Hugging Face
Parameters
27B
Weights (est.)
≈ 16.1 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.
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-OptiQ-4bit --image photo.jpg --prompt "Describe this image"
Details
- Base model
- bottlecapai/ThinkingCap-Qwen3.6-27B (quantized)
- Vendor
- bottlecapai
- Task
- Vision + text
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 357 in the last 30 days · 3.8K all time · 4 likes
- Published
- 2026-07-14 · updated 2026-10-30 (12d ago)
- Tags
- qwen3_5, quantized, mixed-precision, 4bit, 8bit, optiq, apple-silicon, vision-language, qwen3_6, token-efficient, efficient-thinking
Other MLX builds of bottlecapai/ThinkingCap-Qwen3.6-27B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| ThinkingCap-Qwen3.6-27B-OptiQ-4bit (this one) | 4-bit | ≈ 16.1 GB | 24 GB+ | 357 |
| ThinkingCap-Qwen3.6-27B-mlx-6Bit | 6-bit | ≈ 21.9 GB | 32 GB+ | 166 |