NVIDIA releases Qwen3.8-Flash-Next FP4 local model with new lossless compression format
TheZachMueller · x · 2026-10-16
NVIDIA published nvidia/Qwen3.8-Flash-Next-FP4-Local on Hugging Face, an NVFP4-quantized Qwen-based vision-language model under the nvidia open model agreement. The model card notes its NVFP4 scale factors use a new lossless compression format not yet supported by upstream vLLM, so the provided containers are required. Aimed at local deployment.
Related event: NVIDIA's FP4 Qwen3.8-Flash release leaks unannounced model(3 posts)→
More from Infra
- Google's Willow chip cuts quantum errors 40x, raising Q-Day concerns for Bitcoin — jamestagg · 2026-10-16
- Vibe Coding a Data Pipeline Is Easy; Running It at Billions of Rows Is Not — Zachly · 2026-10-16
- Large data centers employ only ~50-150 permanent on-site staff, Microsoft says — brezina · 2026-10-16
- Prediction: Opus 5.5-level models on laptops by 2027, backed by Qwen 27B data — cephaloform · 2026-10-16
- Oracle down 12% in a week, nearly 50% off June high as OpenAI exposure spooks market — alvelda · 2026-10-16
- US data center moratoriums top 400 — an AI bull explains why they're actually good for AI — kevinsxu · 2026-10-16