4-bit Open on Hugging Face
Parameters
561B
Weights (est.)
≈ 315 GB
Mac memory (est.)
512 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/LongCat-Flash-Chat-4bit --prompt "Hello"
Details
- Base model
- meituan-longcat/LongCat-Flash-Chat (quantized)
- Vendor
- meituan-longcat
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- mit
- Downloads
- 31 in the last 30 days · 1.0K all time · 1 likes
- Published
- 2025-09-04 · updated 2025-09-04 (1y ago)
- Tags
- longcat_flash, custom_code
Other MLX builds of meituan-longcat/LongCat-Flash-Chat
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| LongCat-Flash-Chat-4bit (this one) | 4-bit | ≈ 315 GB | 512 GB+ | 31 |
| LongCat-Flash-Chat-bf16 | bf16 | ≈ 1122 GB | > 512 GB | 26 |