FP8-Dynamic quantization using llmcompressor. Run with:
vllm serve leon-se/gemma-3-12b-it-FP8-Dynamic --max-model-len 4096
- Downloads last month
- 1,627
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
HF Inference deployability: The model has no library tag.