Downloads · 30 days
174
2% of all-time downloads
GLM-5.2-MLX-4.5bit
spicyneuron/GLM-5.2-MLX-4.5bit
GLM-5.2-MLX-4.5bit is a text generation model from spicyneuron. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as mit.
zai-org/GLM-5.2 optimized for running on a Mac Studio M3 512.
All-time downloads
8.2K
Public
Parameters
743B
421 GB on disk
Likes
2
Public
Repo makeup
Click a slice to open those files.
.safetensors421 GB · 100%
Parameter types
How the weights are stored.
U32743B · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
zai-org/GLM-5.2 optimized for running on a Mac Studio M3 512.
- A mixed-precision quant that balances speed, memory, and accuracy.
- 4-bit baseline with important layers at higher precision.
- Fits into ~420 GB memory, leaving enough room for a smaller utility model.
Usage
NOTE: Run with https://github.com/ml-explore/mlx-lm/pull/1410 until the PR is merged.
# Start server at http://localhost:8080/v1/chat/completions
uvx --from mlx-lm mlx_lm.server \
--host 127.0.0.1 \
--port 8080 \
--model spicyneuron/GLM-5.2-MLX-4.5bit
Benchmarks
| metric | this model |
|---|---|
| bpw | 4.535 |
| base memory | 392.454 |
| peak memory (1024/512) | 422.787 |
| prompt tok/s (1024) | 194.114 ± 0.079 |
| gen tok/s (512) | 17.781 ± 0.028 |
| kl mean* | 0.049 ± 0.002 |
| kl p95 | 0.113 ± 0.002 |
| perplexity | 4.642 ± 0.036 |
| arc_challenge | 0.690 ± 0.021 |
| hellaswag | 0.780 ± 0.019 |
* KL calculated against the largest quant I could run locally (~5.3 bit). Real KL is against FP will be higher.
Methodology
Quantized with a mlx-lm fork. MLX quantization options differ than llama.cpp, but the principles are the same:
- Sensitive layers like MoE routing, attention, and output embeddings get higher precision
- More tolerant layers like MoE experts get lower precision
- Task
- Text Generation
- Library
- mlx
- Type
- glm_moe_dsa
- License
- mit
- Languages
- en, zh
- Created
- Jun 18, 2026
- Updated
- Jun 19, 2026