meituan-longcat · First MLX build 16 Jan 2026
LongCat-Flash-Thinking-2601
MLX
Text mit
A 561B parameter text generation model from meituan-longcat, with 3 MLX builds, from 4-bit to 8-bit.
- Parameters
- 561B From Hugging Face
- Quantisation
- 4-bit LongCat-Flash-Thinking-2601-4bit
- Memory needed
- 355 GB Estimate, unified memory
- Download
- 315 GB Weights, estimated
- Downloads
- 36 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 3 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 355 GB at 4-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/LongCat-Flash-Thinking-2601-4bit --prompt "Hello"MLX builds
3 on mlx-community| LongCat-Flash-Thinking-2601-4bit | 4-bit | 315 GB | 355 GB | 36 |
|---|---|---|---|---|
| LongCat-Flash-Thinking-2601-6bit | 6-bit | 456 GB | 512 GB | 21 |
| LongCat-Flash-Thinking-2601-8bit | 8-bit | 596 GB | 668 GB | 20 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.