Moonshot AI · First MLX build 20 Apr 2026
Kimi-K2.6
MLX
Text modified-mit
A 1.0T parameter text generation model from Moonshot AI, with 2 MLX builds at 8-bit.
- Parameters
- 1.0T From Hugging Face
- Quantisation
- 8-bit Kimi-K2.6-mlx-DQ3_K_M-q8
- Memory needed
- 1221 GB Estimate, unified memory
- Download
- 1091 GB Weights, estimated
- Downloads
- 839 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 2 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 1221 GB at 8-bit
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · mlx-lm$ pip install -U mlx-lm
$ mlx_lm.generate --model mlx-community/Kimi-K2.6-mlx-DQ3_K_M-q8 --prompt "Hello"MLX builds
2 on mlx-community| Kimi-K2.6-mlx-DQ3_K_M-q8 | 8-bit | 1091 GB | 1221 GB | 839 |
|---|---|---|---|---|
| Kimi-K2.6-MoE-Smart-Quant | Unstated | — | — | 0 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.