Download hf_quant_config.json from local-inference-lab/GLM-5.3-Flash-DFlash2: direct link, hf CLI and curl.
- Browser
- Download file 218 Bytes
-
https://huggingface.co/local-inference-lab/GLM-5.3-Flash-DFlash2/resolve/main/hf_quant_config.json
- Command line
-
hf download hf://local-inference-lab/GLM-5.3-Flash-DFlash2/hf_quant_config.json
-
curl -L -o hf_quant_config.json https://huggingface.co/local-inference-lab/GLM-5.3-Flash-DFlash2/resolve/main/hf_quant_config.json
218 Bytes
| { | |
| "producer": { | |
| "name": "glm53-dflash2-mxfp8-converter", | |
| "version": 1 | |
| }, | |
| "quantization": { | |
| "exclude_modules": [ | |
| "lm_head" | |
| ], | |
| "kv_cache_quant_algo": null, | |
| "quant_algo": "MXFP8" | |
| } | |
| } | |