Kwaipilot · First MLX build 9 Jun 2025
KwaiCoder-AutoThink-preview
MLX
Text kwaipilot-license
A 41B parameter text generation model from Kwaipilot, with 4 MLX builds, from 3-bit to 8-bit.
- Parameters
- 41B From Hugging Face
- Quantisation
- 3-bit KwaiCoder-AutoThink-preview-3bit
- Memory needed
- 22 GB Estimate, unified memory
- Download
- 17.7 GB Weights, estimated
- Downloads
- 48 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 4 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 22 GB at 3-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 · mlx-lm$ pip install -U mlx-lm
$ mlx_lm.generate --model mlx-community/KwaiCoder-AutoThink-preview-3bit --prompt "Hello"MLX builds
4 on mlx-community| KwaiCoder-AutoThink-preview-3bit | 3-bit | 17.7 GB | 22 GB | 48 |
|---|---|---|---|---|
| KwaiCoder-AutoThink-preview-4bit | 4-bit | 22.8 GB | 28 GB | 29 |
| KwaiCoder-AutoThink-preview-6bit | 6-bit | 33.0 GB | 39 GB | 34 |
| KwaiCoder-AutoThink-preview-8bit | 8-bit | 43.1 GB | 51 GB | 26 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.