4-bit Open on Hugging Face
Parameters
6.1B
Weights (est.)
≈ 3.4 GB
Mac memory (est.)
8 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/Yi-6B-Chat-4bit --prompt "Hello"
Details
- Base model
- 01-ai/Yi-6B-Chat (quantized)
- Vendor
- 01.AI · Yi
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 105 in the last 30 days · 399 all time · 0 likes
- Published
- 2024-11-05 · updated 2024-11-05 (2y ago)
- Tags
- llama
Other MLX builds of 01-ai/Yi-6B-Chat
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Yi-6B-Chat-4bit (this one) | 4-bit | ≈ 3.4 GB | 8 GB+ | 105 |
| Yi-6B-Chat-8bit | 8-bit | ≈ 6.4 GB | 16 GB+ | 49 |