MLX Community · First MLX build 13 Sept 2025
glm-4-9b-chat-1m
MLX
Text glm-4
A 9.5B parameter text generation model, with 4 MLX builds, from 4-bit to bf16.
- Parameters
- 9.5B From Hugging Face
- Quantisation
- 4-bit glm-4-9b-chat-1m-4bit
- Memory needed
- 8 GB Estimate, unified memory
- Download
- 5.3 GB Weights, estimated
- Downloads
- 72 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 4 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 8 GB at 4-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/glm-4-9b-chat-1m-4bit --prompt "Hello"MLX builds
4 on mlx-community| glm-4-9b-chat-1m-4bit | 4-bit | 5.3 GB | 8 GB | 72 |
|---|---|---|---|---|
| glm-4-9b-chat-1m-6bit | 6-bit | 7.7 GB | 11 GB | 64 |
| glm-4-9b-chat-1m-8bit | 8-bit | 10.1 GB | 14 GB | 53 |
| glm-4-9b-chat-1m-bf16 | bf16 | 19.0 GB | 24 GB | 44 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.