dual-rtx-6000-blackwell-Gemma-4-31B-IT-NVFP4
theogravity
Optimized vLLM setup for Gemma 4 31B NVFP4 with MTP on dual RTX PRO 6000 Blackwell using vllm and docker: native FP4 Tensor Cores, Multi-Token Prediction (96.5% acceptance rate), and prefix caching. Includes benchmark results and replication scripts.
Growth over time
1 data points · 2026-07-26 → 2026-07-26How do you feel about this project?
Ask AI about dual-rtx-6000-blackwell-Gemma-4-31B-IT-NVFP4
Question copied to clipboardWhat is the theogravity/dual-rtx-6000-blackwell-Gemma-4-31B-IT-NVFP4 GitHub project? Description: "Optimized vLLM setup for Gemma 4 31B NVFP4 with MTP on dual RTX PRO 6000 Blackwell using vllm and docker: native FP4 Tensor Cores, Multi-Token Prediction (96.5% acceptance rate), and prefix caching. Includes benchmark results and replication scripts.". Written in Shell. Explain what it does, its main use cases, key features, and who would benefit from using it.
Question is copied to clipboard — paste it after the AI opens.
How to clone dual-rtx-6000-blackwell-Gemma-4-31B-IT-NVFP4
Clone via HTTPS
Clone via SSH
Download ZIP
Download main.zipFound an issue?
Report bugs or request features on the dual-rtx-6000-blackwell-Gemma-4-31B-IT-NVFP4 issue tracker:
Open GitHub Issues