NVIDIA HF listing for Qwen3.8-Flash-Next-FP4-Local leaks unannounced Qwen3.8 model
TheZachMueller · x · 2026-10-16
An NVIDIA Hugging Face repo named Qwen3.8-Flash-Next-FP4-Local has surfaced, revealing an as-yet unannounced Qwen3.8 Flash Next model. The image-text-to-text checkpoint is quantized to NVFP4 with 8-bit precision scale factors, tagged qwen4exp, and released under the NVIDIA open model agreement. The model card warns that the NVFP4 scale factors use a new lossless compression format not yet supported by upstream vLLM, so users must run it via NVIDIA's provided containers.
More from Models
- PrismML ships Bonsai 2 ternary models: 9B fits in 2GB and beats Qwen3.5 on instruction following — calabi_and_yau · 2026-10-16
- Gemini 4 Argon rolls out globally in Google Search's AI Mode for Pro/Ultra subscribers — OnlineInference · 2026-10-16
- Dev Builds Haunted Escape Room to Test Reflection AI's Beam, Solves It in 30 Seconds — wandb · 2026-10-16
- Claude Opus 5.5 fast mode exits preview: 2.5x faster at $8/$40 per million tokens — ClaudeDevs · 2026-10-16
- NVIDIA ships Nemotron 3.5 Bolt: 74B-A9B model in 24GB of memory — NVIDIAAI · 2026-10-16
- User's Opus 5.5 High Blender 3D experiment crashes their Mac with hilarious results — imjustnewatai · 2026-10-16