Moonshot AI · First MLX build 11 Jul 2025
Kimi-Dev-72B
MLX
Text mit
A 73B parameter text generation model from Moonshot AI, with 5 MLX builds, from 4-bit DWQ to 8-bit.
- Parameters
- 73B From Hugging Face
- Quantisation
- 4-bit DWQ Kimi-Dev-72B-4bit-DWQ
- Memory needed
- 48 GB Estimate, unified memory
- Download
- 40.9 GB Weights, estimated
- Downloads
- 1.8K This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 5 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 48 GB at 4-bit DWQ
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-Dev-72B-4bit-DWQ --prompt "Hello"MLX builds
5 on mlx-community| Kimi-Dev-72B-4bit-DWQ | 4-bit DWQ | 40.9 GB | 48 GB | 1.8K |
|---|---|---|---|---|
| Kimi-Dev-72B-4bit | 4-bit | 40.9 GB | 48 GB | 208 |
| Kimi-Dev-72B-5bit | 5-bit | 50.0 GB | 58 GB | 154 |
| Kimi-Dev-72B-6bit | 6-bit | 59.1 GB | 69 GB | 113 |
| Kimi-Dev-72B-8bit | 8-bit | 77.3 GB | 89 GB | 150 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.