KwaiCoder-AutoThink-preview-4bit
mlx-community/KwaiCoder-AutoThink-preview-4bit
Text generation · mlx
4-bit Open on Hugging Face
Parameters
41B
Weights (est.)
≈ 22.8 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-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/KwaiCoder-AutoThink-preview-4bit --prompt "Hello"
Details
- Base model
- Kwaipilot/KwaiCoder-AutoThink-preview (quantized)
- Vendor
- Kwaipilot
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- kwaipilot-license
- Downloads
- 30 in the last 30 days · 164 all time · 0 likes
- Published
- 2025-06-09 · updated 2025-06-09 (1y ago)
- Languages
- multilingual
- Tags
- qwen2
Other MLX builds of Kwaipilot/KwaiCoder-AutoThink-preview
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| KwaiCoder-AutoThink-preview-3bit | 3-bit | ≈ 17.7 GB | 24 GB+ | 48 |
| KwaiCoder-AutoThink-preview-4bit (this one) | 4-bit | ≈ 22.8 GB | 32 GB+ | 30 |
| KwaiCoder-AutoThink-preview-6bit | 6-bit | ≈ 33.0 GB | 48 GB+ | 33 |
| KwaiCoder-AutoThink-preview-8bit | 8-bit | ≈ 43.1 GB | 64 GB+ | 27 |