nvidia/Qwen3.8-Flash-Next-NVFP4 — new model trending #28 on Hugging Face
NVIDIA released an NVFP4 4-bit quantized build of Alibaba's Qwen3.8-Flash-Next, a 125B-parameter MoE vision-language model, via Model Optimizer.
The checkpoint quantizes Qwen3.8-Flash-Next — a hybrid-attention (Gated DeltaNet and Qwen Sparse Attention) Mixture-of-Experts model with 125B total and 6B activated parameters, plus 51B n-gram embeddings and 4B MTP — using NVIDIA Model Optimizer v0.46.0. NVFP4 benchmarks stay close to FP8: GPQA Diamond 91.5 vs 92.0, MMMU Pro 78.3 vs 77.1, Terminal-Bench 2.1 82.9 vs 83.3. It targets Blackwell B200/B300 GPUs, runs on vLLM, supports 262K context extendable to 1M tokens, and is licensed under the NVIDIA Open Model License with Qwen Community License 1.0.
- NVFP4 matches or slightly beats FP8 on several benchmarks, including MMMU Pro and AA-LCR
- Accepts text, image, and video input; aimed at agents, chatbots, and RAG deployments
- Calibrated on cnn_dailymail and Nemotron-Post-Training-Dataset-v2
From the original article
6 min read at huggingface.coimage-text-to-text · 26,302 downloads · 148 likes · license other
By nvidia · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.