LongWriter-llama3.1-8b-6bit
mlx-community/LongWriter-llama3.1-8b-6bit
Text generation · transformers
6-bit Open on Hugging Face
Parameters
8.0B
Weights (est.)
≈ 6.5 GB
Mac memory (est.)
16 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/LongWriter-llama3.1-8b-6bit --prompt "Hello"
Details
- Base model
- zai-org/LongWriter-llama3.1-8b (quantized)
- Vendor
- zai-org
- Task
- Text generation
- Quantisation
- 6-bit
- Licence
- llama3.1
- Downloads
- 70 in the last 30 days · 643 all time · 2 likes
- Published
- 2025-09-28 · updated 2025-09-28 (1y ago)
- Languages
- en, zh
- Tags
- llama, Long Context, chatglm, mlx-my-repo
Other MLX builds of zai-org/LongWriter-llama3.1-8b
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| LongWriter-llama3.1-8b-6bit (this one) | 6-bit | ≈ 6.5 GB | 16 GB+ | 70 |
| LongWriter-llama3.1-8b-8bit | 8-bit | ≈ 8.5 GB | 16 GB+ | 47 |