deepseek-ai / text-generation updated 2 months ago

DeepSeek-V4-Pro

Name: DeepSeek-V4-Pro
Author: deepseek-ai

We present a preview version of DeepSeek-V4 series, including two strong Mixture-of-Experts (MoE) language models — DeepSeek-V4-Pro with 1.6T parameters (49B activated) and DeepSeek-V4-Flash with 284B parameters (13B activated) — both supporting a context length of one million tokens.

Params

1,598.8 B

Context

1,048,576

Downloads 30d

569 K

Likes

5,582

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

Download history

daily snapshots · 56 days

▲ 583 K in the last 30 days (50.6%)

1.7 M569 K

Jul 28Aug 15Sep 3Sep 21

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	i8	864.7 GB	1,191.5 GB	❌ Won’t fit
model.safetensors (bf16, full)	bf16 + 1024K ctx	864.7 GB	31,649.4 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-v4-pro
{
  "hf_id": "deepseek-ai/DeepSeek-V4-Pro",
  "params_b": 1598.84,
  "context_length": 1048576,
  "license": { "id": "mit", "commercial": "yes" },
  "downloads_30d": 569497,
  "vram_estimates": [
    { "quant": "i8", "gb": 1191.5 }
  ],
  "updated_at": "2026-07-28T18:03:02Z"
}

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

Specifications

Architecture: DeepseekV4ForCausalLM
Parameters: 1,598.8 B
Tensor type: I8
Context length: 1,048,576
Vocabulary: 129,280
Layers / heads: 61 / 128
Licence: mit
First seen on the Hub: 2026-04-22
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Compare with any text-generation model

Popular comparisons

DeepSeek-V3.2 2.5 M DeepSeek-V3 1.1 M DeepSeek-V3-0324 1.0 M GLM-5.2-FP8 978 K GLM-5.3 974 K GLM-5.2 962 K