AtlasAI Center AI tool intelligence
NVIDIA · Open-weight model

DeepSeek V4.1 Flash NVFP4

DeepSeek V4.1 Flash NVFP4 is a image-text-to-text model published on Hugging Face by nvidia.

Downloads (30d)
15,925
Released
Sep 16, 2026
Specifications

DeepSeek V4.1 Flash NVFP4 specs

Provider
NVIDIA
Type
Open-weight model
Model ID
nvidia/DeepSeek-V4.1-Flash-NVFP4
Task
image text to text
Released
Sep 16, 2026
License
mit
Architecture
Model Optimizer
Base model
deepseek-ai/DeepSeek-V4.1-Flash
Downloads
15,925Hugging Face, last 30 days
Likes
90
Source
Hugging Face
Overview

About DeepSeek V4.1 Flash NVFP4

DeepSeek V4.1 Flash NVFP4 is an open-weight model from NVIDIA, released on Sep 16, 2026, with the mit license, 15,925 Hugging Face downloads in the last 30 days.

Specs are sourced from Hugging Face and were last checked on Sep 24, 2026. Always confirm current pricing and limits with the provider before production use.

FP8 weightsQuantized
FAQ

DeepSeek V4.1 Flash NVFP4 questions

When was DeepSeek V4.1 Flash NVFP4 released?

DeepSeek V4.1 Flash NVFP4 was published on Sep 16, 2026.

Can I run DeepSeek V4.1 Flash NVFP4 locally?

DeepSeek V4.1 Flash NVFP4 is published as an open-weight model on Hugging Face under the mit license, so you can download the weights and run them on compatible hardware, subject to the license terms.