4-bit Open on Hugging Face
Parameters
1.0T
Weights (est.)
≈ 578 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/Kimi-K2-Instruct-4bit --prompt "Hello"
Details
- Base model
- moonshotai/Kimi-K2-Instruct (quantized) · Kimi K2 Instruct on the radar →
- Vendor
- Moonshot · Kimi
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- modified-mit
- Downloads
- 1.2K in the last 30 days · 125K all time · 13 likes
- Published
- 2025-07-11 · updated 2025-07-11 (1y ago)
- Tags
- kimi_k2, custom_code
Other MLX builds of moonshotai/Kimi-K2-Instruct
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| moonshotai_Kimi-K2-Instruct-mlx-3bit | 3-bit | ≈ 449 GB | 512 GB+ | 219 |
| Kimi-K2-Instruct-4bit (this one) | 4-bit | ≈ 578 GB | > 512 GB | 1.2K |