NVIDIA's NVFP4-quantized Qwen3.8-Flash-Next image-text-to-text model trends on Hugging Face

nvidia · hf · 2026-09-05

NVIDIA released Qwen3.8-Flash-Next-NVFP4 on Hugging Face, where it is trending. The model is an FP4-quantized build of Qwen3.8 produced with NVIDIA's Model Optimizer (ModelOpt), distributed in safetensors format with an image-text-to-text pipeline, targeting low-precision multimodal inference deployment.

Related event: NVIDIA Releases NVFP4 Quantized Qwen3.8-Flash-Next(2 posts)→

Original post →

More from Models

Models channel →