4-bit Open on Hugging Face
Parameters
69B
Weights (est.)
≈ 38.6 GB
Mac memory (est.)
48 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-Lite-Sparse-4bit --prompt "Hello"
Details
- Base model
- meituan-longcat/LongCat-Flash-Lite-Sparse (quantized)
- Vendor
- meituan-longcat
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- mit
- Downloads
- 76 in the last 30 days · 631 all time · 1 likes
- Published
- 2026-08-28 · updated 2026-08-31 (2mo ago)
- Languages
- en, zh
- Tags
- longcat_flash_sparse, longcat, ngram-embedding
Other MLX builds of meituan-longcat/LongCat-Flash-Lite-Sparse
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| LongCat-Flash-Lite-Sparse-4bit (this one) | 4-bit | ≈ 38.6 GB | 48 GB+ | 76 |
| LongCat-Flash-Lite-Sparse-6bit | 6-bit | ≈ 55.7 GB | 96 GB+ | 61 |
| LongCat-Flash-Lite-Sparse-8bit | 8-bit | ≈ 72.9 GB | 96 GB+ | 51 |