deepseek-ai / text-generation updated 11 months ago

DeepSeek-V3.1

Name: DeepSeek-V3.1
Author: deepseek-ai

DeepSeek-V3.1 is a hybrid model that supports both thinking mode and non-thinking mode. Compared to the previous version, this upgrade brings improvements in multiple aspects:

Params

684.5 B

Context

163,840

Downloads 30d

268 K

Likes

826

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

Download history

daily snapshots · 10 days

293 K268 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	f8_e4m3	688.6 GB	860.6 GB	❌ Won’t fit
model.safetensors (bf16, full)	bf16 + 160K ctx	688.6 GB	2,811.5 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-v3-1
{
  "hf_id": "deepseek-ai/DeepSeek-V3.1",
  "params_b": 684.53,
  "context_length": 163840,
  "license": { "id": "mit", "commercial": "yes" },
  "downloads_30d": 267744,
  "vram_estimates": [
    { "quant": "f8_e4m3", "gb": 860.6 }
  ],
  "updated_at": "2026-07-28T18:06:46Z"
}

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

Specifications

Architecture: DeepseekV3ForCausalLM
Parameters: 684.5 B
Tensor type: F8_E4M3
Context length: 163,840
Vocabulary: 129,280
Layers / heads: 61 / 128
Licence: mit
First seen on the Hub: 2025-08-21
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Compare with

DeepSeek-R1 9.9 M GLM-5.2-FP8 2.7 M GLM-5.2 2.2 M DeepSeek-V3.2 1.2 M DeepSeek-V3 1.2 M GLM-5-FP8 1.2 M

Appears in

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