LLM EXPLORER 58,531 MODELS INDEXED

DeepSeek V3.2 NVFP4 by nvidia

By nvidia · 7012 downloads
HF Repo ↗ Copy URL

DeepSeek V3.2 NVFP4 is an open-source language model by nvidia. Features: 394.5b LLM, VRAM: 106.1GB, Context: 160K, License: mit, LLM Explorer Score: 0.26.

  8-bit Base model:deepseek-ai/deepsee... Base model:finetune:deepseek-a...   Deepseek v32   Deepseekv3.2   Model optimizer   Modelopt   Nvfp4   Nvidia   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/nvidia/DeepSeek-V3.2-NVFP4 

DeepSeek V3.2 NVFP4 Parameters and Internals

LLM NameDeepSeek V3.2 NVFP4
Repository 🤗https://huggingface.co/nvidia/DeepSeek-V3.2-NVFP4 
Base Model(s)  deepseek-ai/DeepSeek-V3.2   deepseek-ai/DeepSeek-V3.2
Model Size394.5b
Required VRAM106.1 GB
Updated2026-07-30
Maintainernvidia
Model Typedeepseek_v32
Model Files  4.2 GB: 1-of-163   2.4 GB: 2-of-163   2.4 GB: 3-of-163   2.5 GB: 4-of-163   2.4 GB: 5-of-163   2.5 GB: 6-of-163   2.5 GB: 7-of-163   2.4 GB: 8-of-163   2.5 GB: 9-of-163   2.4 GB: 10-of-163   2.4 GB: 11-of-163   0.8 GB: 12-of-163   2.5 GB: 13-of-163   2.4 GB: 14-of-163   2.5 GB: 15-of-163   2.4 GB: 16-of-163   2.4 GB: 17-of-163   2.5 GB: 18-of-163   2.4 GB: 19-of-163   2.4 GB: 20-of-163   2.5 GB: 21-of-163   2.4 GB: 22-of-163   2.5 GB: 23-of-163   2.4 GB: 24-of-163   2.4 GB: 25-of-163   2.5 GB: 26-of-163   2.4 GB: 27-of-163   2.4 GB: 28-of-163   2.5 GB: 29-of-163   2.4 GB: 30-of-163   2.5 GB: 31-of-163   2.4 GB: 32-of-163   2.4 GB: 33-of-163   1.1 GB: 34-of-163   2.5 GB: 35-of-163   2.4 GB: 36-of-163   2.5 GB: 37-of-163   2.4 GB: 38-of-163   2.4 GB: 39-of-163   2.5 GB: 40-of-163   2.4 GB: 41-of-163   2.4 GB: 42-of-163   2.5 GB: 43-of-163   2.4 GB: 44-of-163
Model ArchitectureDeepseekV32ForCausalLM
Licensemit
Context Length163840
Model Max Length163840
Transformers Version4.44.2
Vocabulary Size129280
Torch Data Typebfloat16