GLM-5.2-oQ4
This model was quantized using oQ (oMLX v0.4.5.dev1) mixed-precision quantization.
Quantization details
- Model type: glm_moe_dsa
- Bits: 4
- Group size: 64
- Format: MLX safetensors
- Downloads last month
- 4,046
Model size
119B params
Tensor type
BF16
路
U32 路
F32 路
Hardware compatibility
Log In to add your hardware
4-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir GLM-5.2-oQ4 Jundot/GLM-5.2-oQ4