A collection of bookmarks filtered by the tag "NVFP4 Quantization".
Showing 1-2 of 2 bookmarks tagged with "NVFP4 Quantization"
All Stories
qwen38-flash-next recipe for solo GB10. Contribute to bilikaz/qwen38-flash-next-recipe development by creating an account on GitHub.
Deploy Qwen3.8-27B with SGLang — dense hybrid GDN vision-language model with BF16/FP8/NVFP4 W4A4 checkpoints and in-checkpoint MTP, single-GPU on H200...
Community recipes for serving LLMs on RTX 3090. Multi-engine (vLLM, llama.cpp, SGLang) and model-agnostic. Currently shipping Qwen3.6-27B configs for ...
