Downloads · 30 days
30
9% of all-time downloads
DeepSeek-V4-Flash-0731-NVFP4
axiomofmind/DeepSeek-V4-Flash-0731-NVFP4
DeepSeek-V4-Flash-0731-NVFP4 is a text generation model from axiomofmind. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as mit.
An independently calibrated NVIDIA NVFP4 export of deepseek-ai/DeepSeek-V4-Flash-0731.
All-time downloads
319
Public
Parameters
304B
176 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors176 GB · 100%
Parameter types
How the weights are stored.
U8277B · 91%
Try a prompt
Base models
Model card
From the Hugging Face model README
DeepSeek-V4-Flash-0731 NVFP4
An independently calibrated NVIDIA NVFP4 export of
deepseek-ai/DeepSeek-V4-Flash-0731.
The 43 routed-expert layers (256 experts each) use NVFP4 weights and calibrated activation scales. Attention, shared experts, router, embeddings, output head, and the attached speculative/MTP module retain their source formats. The source MXFP4 expert values were converted losslessly to NVFP4 representation; activation scales were calibrated separately.
Calibration
- NVIDIA ModelOpt, eight H100 80 GB GPUs
- 128 samples at up to 512 tokens: 32 each from CNN/DailyMail, OpenCodeReasoning, OpenMathReasoning, and Magpie-Pro-MT-300K
- 65,536 padded sequence positions
- Max calibration algorithm, batch size 1
See CONVERSION.md for exact revisions, commands, export statistics, and audit
results. This repository contains the Hugging Face NVFP4 checkpoint, not GGUF.
Runtime support for this DeepSeek V4 NVFP4 layout is required.
The original model's MIT license is included. Model architecture, usage, chat format, and limitations are documented in the official model card.
- Task
- Text Generation
- Library
- transformers
- Type
- deepseek_v4
- License
- mit
- Created
- Aug 22, 2026
- Updated
- Aug 22, 2026