8-bit Open on Hugging Face
Parameters
1.0T
Weights (est.)
≈ 1091 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-K2.6-mlx-DQ3_K_M-q8 --prompt "Hello"
Details
- Base model
- moonshotai/Kimi-K2.6 (quantized) · Kimi K2.6 on the radar →
- Vendor
- Moonshot · Kimi
- Task
- Text generation
- Quantisation
- 8-bit
- Licence
- modified-mit
- Downloads
- 933 in the last 30 days · 370K all time · 9 likes
- Published
- 2026-04-21 · updated 2026-04-21 (6mo ago)
- Tags
- kimi_k25, feature-extraction, custom_code
Other MLX builds of moonshotai/Kimi-K2.6
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Kimi-K2.6-mlx-DQ3_K_M-q8 (this one) | 8-bit | ≈ 1091 GB | > 512 GB | 933 |
| Kimi-K2.6-MoE-Smart-Quant | — | — | — | 0 |