What are the hardware requirements for DeepSeek R1 FP4 V2?

DeepSeek R1 FP4 V2 requires approximately 103.5 GB of VRAM and supports a context window of 160K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed DeepSeek R1 FP4 V2 and how large is it?

DeepSeek R1 FP4 V2 is developed by nvidia, a model with 393.6b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate DeepSeek R1 FP4 V2?

DeepSeek R1 FP4 V2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

DeepSeek R1 FP4 V2 by nvidia — VRAM 103.5GB, 160K context

Name: DeepSeek R1 FP4 V2
Author: nvidia

DeepSeek R1 FP4 V2 is an open-source language model by nvidia. Features: 393.6b LLM, VRAM: 103.5GB, Context: 160K, License: mit, LLM Explorer Score: 0.2.

8-bit Base model:deepseek-ai/deepsee... Base model:finetune:deepseek-a... Conversational Custom code Deepseek v3 Deepseekr1 Fp4 Model optimizer Modelopt Nvidia Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/nvidia/DeepSeek-R1-FP4-v2

DeepSeek R1 FP4 V2 Parameters and Internals

LLM Name	DeepSeek R1 FP4 V2
Repository 🤗	https://huggingface.co/nvidia/DeepSeek-R1-FP4-v2
Base Model(s)	DeepSeek R1 deepseek-ai/DeepSeek-R1
Model Size	393.6b
Required VRAM	103.5 GB
Updated	2025-09-23
Maintainer	nvidia
Model Type	deepseek_v3
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 2.6 GB: 6-of-163 2.4 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 0.7 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 1.0 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
Model Architecture	DeepseekV3ForCausalLM
License	mit
Context Length	163840
Model Max Length	163840
Transformers Version	4.46.3
Vocabulary Size	129280
Torch Data Type	bfloat16

Rank the DeepSeek R1 FP4 V2 capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to DeepSeek R1 FP4 V2

Best Alternatives	Context / RAM	Downloads	Likes
DeepSeek R1 0528 NVFP4 V2	160K / 103.5 GB	321229	23
DeepSeek V3.1 NVFP4	160K / 103.5 GB	52609	15
DeepSeek R1 0528 FP4 V2	160K / 103.5 GB	70194	8
DeepSeek R1 NVFP4 V2	160K / 103.5 GB	417	8

Note: green Score (e.g. "73.2") means that the model is better than nvidia/DeepSeek-R1-FP4-v2.