NVIDIAAnalysisAI ModelsNovember 19, 2026

Nvidia posts NVFP4-quantized Qwen3.8 27B and Flash-Next checkpoints

Read original source →huggingface.co

Nvidia published NVFP4-QAD quantizations of Qwen3.8-27B and Qwen3.8-Flash-Next to Hugging Face, surfaced on r/LocalLLaMA. Both are community-facing weight uploads rather than new model releases.

2 sources

More stories today

Open the live feed