deepseek-ai / text-generation updated 8 months ago

DeepSeek-V3.2

Name: DeepSeek-V3.2
Author: deepseek-ai

We introduce DeepSeek-V3.2, a model that harmonizes high computational efficiency with superior reasoning and agent performance. Our approach is built upon three key technical breakthroughs:

Params

685.4 B

Context

163,840

Downloads 30d

1.2 M

Likes

1,463

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

Download history

daily snapshots · 10 days

1.3 M1.2 M

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	689.5 GB	861.7 GB	❌ Won’t fit
model.safetensors (bf16, full)	bf16 + 160K ctx	689.5 GB	2,815.1 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-v3-2
{
  "hf_id": "deepseek-ai/DeepSeek-V3.2",
  "params_b": 685.40,
  "context_length": 163840,
  "license": { "id": "mit", "commercial": "yes" },
  "downloads_30d": 1246445,
  "vram_estimates": [
    { "quant": "f8_e4m3", "gb": 861.7 }
  ],
  "updated_at": "2026-07-28T18:03:19Z"
}

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

Specifications

Architecture: DeepseekV32ForCausalLM
Parameters: 685.4 B
Tensor type: F8_E4M3
Context length: 163,840
Vocabulary: 129,280
Layers / heads: 61 / 128
Licence: mit
First seen on the Hub: 2025-12-01
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Family

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

Derivative DeepSeek-V3.2-AWQ QuantTrio 168 K

Compare with

DeepSeek-R1 9.9 M GLM-5.2-FP8 2.7 M GLM-5.2 2.2 M GLM-5.2-NVFP4 1.8 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