marcbuils's picture
[Usage]: Tool calling for gemma-3
424be11 verified
|
Raw History Blame Contribute Delete
219 Bytes
metadata
license: gemma
base_model:
  - leon-se/gemma-3-27b-it-FP8-Dynamic

FP8-Dynamic quantization using llmcompressor. Run with:

vllm serve marcbuils/gemma-3-27b-it-FP8-Dynamic-tools --max-model-len 4096