Qwen3.8 Flash Next FP4 Local
Image text to text model by nvidia
Qwen3.8 Flash Next FP4 Local launched on 8 October 2026. It ranked #56 on Daily Launch on 22 October 2026 with a Launch Score of 37, from trending score 287 on Hugging Face. It moved up 8 places from the day before.
What is Qwen3.8 Flash Next FP4 Local?
IMPORTANT: the NVFP4 scale factors in this checkpoint are in a new lossless compression format, but upstream vLLM support for this format has not yet landed. You must use one of the containers provided below. The checkpoint occupies approximately 96 GiB on disk and is best suited for local AI hardware. It has been validated with vLLM on the following hardware: NVIDIA RTX PRO 6000 Blackwell — single GPU, with PLE (n-gram embedding table) offload.
From its model card on Hugging Face
Qwen3.8 Flash Next FP4 Local is a model by nvidia on Hugging Face. It is released under the nvidia-open-model-agreement license.
How to get Qwen3.8 Flash Next FP4 Local
Get it from its model card on Hugging Face.