wowsuch ai
Live

NVIDIAModel

Qwen3.8-Flash-Next NVFP4

Qwen3.8-Flash-Next NVFP4 is a mixed-precision, post-training-quantized checkpoint of the Qwen3.8-Flash-Next multimodal causal language model prepared with NVIDIA Model Optimizer. It provides a smaller, GPU-accelerated checkpoint intended for deployment with vLLM on NVIDIA Blackwell GPUs and supports long-context multimodal (text, image, video) inputs with text outputs.

What it does

Developers can run it locally for AI agents, chatbots, RAG systems, and other AI-powered applications.

Availability
Released on Hugging Face 10/05/2026
Pricing model
free
Deployment
Local deployment; validated on NVIDIA DGX Spark and NVIDIA RTX PRO 6000 Blackwell
Privacy
governed by NVIDIA Open Model License; refers to Qwen Community License 1.0
Licence
NVIDIA Open Model Agreement; base model governed by Qwen Community License 1.0
Capability
text generationanalysiscode generationagents
Modality
textimagevideomultimodal
Access
open weights
Deployment
on-premises
Pricing
unknown
Target user
developerresearcherenterprise

Evidence

12 claims
  • The repository contains model weights and configuration files for the post-trained model. [1]
    > This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format.
    Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights.
  • The model artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, and TokenSpeed. [1]
    > These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, TokenSpeed, etc.
    Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights.
  • The NVFP4 1.0 checkpoint was released on Hugging Face on 08/31/2026. [2]
    The model version is NVFP4 1.0 and was produced with nvidia-modelopt **v0.46.0**.
    NVIDIA. Quoted text is outside CC BY 4.0 and keeps its original rights.
  • The model supports vLLM and is listed as compatible with NVIDIA Blackwell B200 and B300. [2]
  • The NVFP4 checkpoint is approximately 2.7 times smaller than the BF16 source checkpoint. [2]
    The resulting checkpoint is approximately 2.7x smaller than the BF16 source checkpoint (about a 63% reduction in disk size).
    NVIDIA. Quoted text is outside CC BY 4.0 and keeps its original rights.
  • The model is ready for commercial or non-commercial use under the stated NVIDIA Open Model License and Qwen Community License 1.0. [2]
  • The model checkpoint is available on Hugging Face. [3]
    The Nemotron-Pre-Training-Datasets collection on Hugging Face provides large-scale data corpora used to train the NVIDIA Nemotron model family <br>
    NVIDIA. Quoted text is outside CC BY 4.0 and keeps its original rights.
  • The model accepts text, image, and video input and produces text output. [3]
    **Input Type(s):** Text, Image, Video <br>
    NVIDIA. Quoted text is outside CC BY 4.0 and keeps its original rights.
  • The approximately 96 GiB checkpoint is best suited for local AI hardware. [3]
    The checkpoint occupies approximately **96 GiB on disk** and is best suited for local AI hardware.
    NVIDIA. Quoted text is outside CC BY 4.0 and keeps its original rights.
  • The model has been validated with vLLM on NVIDIA DGX Spark and NVIDIA RTX PRO 6000 Blackwell. [3]
    **Test Hardware:** NVIDIA DGX Spark and NVIDIA RTX PRO 6000 Blackwell
    NVIDIA. Quoted text is outside CC BY 4.0 and keeps its original rights.
  • The checkpoint requires one of the provided containers because upstream vLLM support for its NVFP4 scale-factor format has not yet landed. [3]
    **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.
    NVIDIA. Quoted text is outside CC BY 4.0 and keeps its original rights.
  • The model is ready for commercial or non-commercial use. [3]
    This model is ready for commercial or non-commercial use.
    NVIDIA. Quoted text is outside CC BY 4.0 and keeps its original rights.

Sources

3
1
Hugging FaceOwner-controlled
https://huggingface.co/Qwen/Qwen3.8-Flash-Next Retrieved 2026-10-27 01:17 UTC
Verified
2
NVIDIAOwner-controlled
https://huggingface.co/nvidia/Qwen3.8-Flash-Next-NVFP4 Retrieved 2026-10-27 01:17 UTC
Verified
3
NVIDIAOwner-controlled
https://huggingface.co/nvidia/Qwen3.8-Flash-Next-FP4-Local Retrieved 2026-10-27 01:17 UTC
Verified

Versions

58
VersionEffectiveChangeChanged fieldsState
582026-10-27 01:17 UTCmaterial changemodality, availability, deploymentCurrent
572026-10-27 01:17 UTCmaterial changemodality, availability, deploymentCurrent
562026-10-26 00:38 UTCevidence updatescoreCurrent
552026-10-26 00:38 UTCmaterial changemodality, availability, deploymentCurrent
542026-10-26 00:38 UTCmaterial changemodality, availability, deploymentCurrent
532026-10-25 00:47 UTCmaterial changemodality, availability, deploymentCurrent
522026-10-25 00:47 UTCmaterial changemodality, availability, deploymentCurrent
512026-10-24 01:17 UTCevidence updatescoreCurrent
502026-10-24 01:17 UTCmaterial changemodality, availability, deploymentCurrent
492026-10-24 01:17 UTCmaterial changemodality, availability, deploymentCurrent
482026-10-23 00:58 UTCmaterial changemodality, availability, deploymentCurrent
472026-10-23 00:58 UTCmaterial changemodality, availability, deploymentCurrent
462026-10-22 00:28 UTCevidence updatescoreCurrent
452026-10-22 00:28 UTCmaterial changemodality, availability, deploymentCurrent
442026-10-22 00:28 UTCmaterial changemodality, availability, deploymentCurrent
432026-10-20 16:32 UTCmaterial changemodality, availability, deploymentCurrent
422026-10-20 16:32 UTCmaterial changemodality, availability, deploymentCurrent
412026-10-19 17:30 UTCevidence updatescoreCurrent
402026-10-19 17:30 UTCmaterial changemodality, availability, deploymentCurrent
392026-10-19 17:30 UTCmaterial changemodality, availability, deploymentCurrent
382026-10-18 18:19 UTCmaterial changemodality, availability, deploymentCurrent
372026-10-18 18:19 UTCmaterial changemodality, availability, deploymentCurrent
362026-10-17 19:10 UTCevidence updatescoreCurrent
352026-10-17 19:10 UTCmaterial changemodality, availability, deploymentCurrent
342026-10-17 19:10 UTCmaterial changemodality, availability, deploymentCurrent
332026-10-16 20:05 UTCmaterial changemodality, availability, deploymentCurrent
322026-10-16 20:05 UTCmaterial changemodality, availability, deploymentCurrent
312026-10-15 22:33 UTCevidence updatescoreCurrent
302026-10-15 20:56 UTCmaterial changemodality, availability, deploymentCurrent
292026-10-14 21:47 UTCevidence updatescoreCurrent
282026-10-14 21:47 UTCmaterial changemodality, availability, deploymentCurrent
272026-10-13 22:39 UTCmaterial changemodality, availability, deploymentCurrent
262026-10-12 23:32 UTCevidence updatescoreCurrent
252026-10-12 23:32 UTCmaterial changemodality, availability, deploymentCurrent
242026-10-12 00:28 UTCmaterial changemodality, availability, deploymentCurrent
232026-10-11 01:22 UTCmaterial changemodality, availability, deploymentCurrent
222026-10-10 02:15 UTCmaterial changemodality, availability, deploymentCurrent
212026-10-09 03:11 UTCevidence updatescoreCurrent
202026-10-09 03:11 UTCmaterial changemodality, availability, deploymentCurrent
192026-10-08 04:06 UTCmaterial changemodality, availability, deploymentCurrent
182026-10-07 05:02 UTCmaterial changemodality, availability, deploymentCurrent
172026-10-06 05:53 UTCmaterial changemodality, availability, deploymentCurrent
162026-10-05 06:49 UTCmaterial changemodality, availability, deploymentCurrent
152026-10-04 07:45 UTCmaterial changemodality, availability, deploymentCurrent
142026-10-03 08:42 UTCmaterial changemodality, availability, deploymentCurrent
132026-10-02 09:37 UTCmaterial changemodality, availability, deploymentCurrent
122026-10-01 10:28 UTCevidence updatescoreCurrent
112026-10-01 10:28 UTCmaterial changemodality, availability, deploymentCurrent
102026-09-30 11:22 UTCmaterial changemodality, availability, deploymentCurrent
92026-09-29 12:16 UTCmaterial changemodality, availability, deploymentCurrent
82026-09-28 13:05 UTCmaterial changemodality, availability, deploymentCurrent
72026-09-27 14:01 UTCevidence updatescoreCurrent
62026-09-27 14:01 UTCmaterial changemodality, availability, deploymentCurrent
52026-09-26 14:55 UTCmaterial changemodality, availability, deploymentCurrent
42026-09-25 15:48 UTCmaterial changemodality, availability, deploymentCurrent
32026-09-24 16:39 UTCmaterial changemodality, access, deployment, pricing, availability, deploymentCurrent
22026-09-24 16:39 UTCmaterial changemodality, access, deployment, pricing, availability, deploymentCurrent
12026-09-23 17:33 UTCpublicationNoneCurrent

In briefs

1

Open in the catalog

Original catalog content is licensed under CC BY 4.0, attributed to wowsuchai. Source quotations and linked content keep their original rights.