bf16 Open on Hugging Face
Parameters
9.5B
Weights (est.)
≈ 19.0 GB
Mac memory (est.)
24 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/glm-4-9b-chat-1m-bf16 --prompt "Hello"
Details
- Base model
- zai-org/glm-4-9b-chat-1m-hf (finetune)
- Vendor
- zai-org
- Task
- Text generation
- Quantisation
- bf16
- Licence
- glm-4
- Downloads
- 46 in the last 30 days · 935 all time · 1 likes
- Published
- 2025-09-13 · updated 2025-09-14 (1y ago)
- Languages
- en, zh
- Tags
- chatglm
Other MLX builds of zai-org/glm-4-9b-chat-1m-hf
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| glm-4-9b-chat-1m-4bit | 4-bit | ≈ 5.3 GB | 8 GB+ | 74 |
| glm-4-9b-chat-1m-6bit | 6-bit | ≈ 7.7 GB | 16 GB+ | 65 |
| glm-4-9b-chat-1m-8bit | 8-bit | ≈ 10.1 GB | 16 GB+ | 56 |
| glm-4-9b-chat-1m-bf16 (this one) | bf16 | ≈ 19.0 GB | 24 GB+ | 46 |