nvidia / text-generation updated 11 months ago

DeepSeek-R1-0528-NVFP4-v2

Name: DeepSeek-R1-0528-NVFP4-v2
Author: nvidia

The NVIDIA DeepSeek-R1-0528-FP4 v2 model is the quantized version of the DeepSeek AI's DeepSeek R1 0528 model, which is an auto-regressive language model that uses an optimized transformer architecture. For more information, please check here. The NVIDIA DeepSeek R1 FP4 model is quantized with TensorRT Model Optimizer.

Params

393.6 B

Context

163,840

Downloads 30d

325 K

Likes

Commercial use: allowed mit Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 10 days

384 K321 K

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	u8	413.3 GB	514.2 GB	❌ Won’t fit
model.safetensors (bf16, full)	bf16 + 160K ctx	413.3 GB	1,636.1 GB	❌ Won’t fit

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub

~ · curl · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/deepseek-r1-0528-nvfp4-v2
{
  "hf_id": "nvidia/DeepSeek-R1-0528-NVFP4-v2",
  "params_b": 393.63,
  "context_length": 163840,
  "license": { "id": "mit", "commercial": "yes" },
  "downloads_30d": 324770,
  "vram_estimates": [
    { "quant": "u8", "gb": 514.2 }
  ],
  "updated_at": "2026-07-28T18:05:56Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture: DeepseekV3ForCausalLM
Parameters: 393.6 B
Tensor type: U8
Context length: 163,840
Vocabulary: 129,280
Layers / heads: 61 / 128
Licence: mit
First seen on the Hub: 2025-07-21
Base model: DeepSeek-R1-0528
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Family

Base model and the most-downloaded derivatives in the catalog.

Base DeepSeek-R1-0528 deepseek-ai 210 K

Compare with

DeepSeek-R1 9.9 M gpt-oss-120b 4.2 M DeepSeek-V4-Flash 2.7 M GLM-5.2-FP8 2.7 M GLM-5.2 2.2 M GLM-5.2-NVFP4 1.8 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB