GLM-5.3-Flash Quantizations
Collection
oQ mixed-precision MLX quantizations of GLM-5.3-Flash with MTP (oMLX) โข 6 items โข Updated
How to use gabmiranda/GLM-5.3-Flash-oQ3e-mtp with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download gabmiranda/GLM-5.3-Flash-oQ3e-mtp --local-dir GLM-5.3-Flash-oQ3e-mtp
Base model
zai-org/GLM-5.3-Flash