deepseek-ai / text-generation Open weights Also via API updated 11 months ago

DeepSeek-V3.2

Name: DeepSeek-V3.2
Price: 0.26 USD
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

7.6 M

Likes

1,597

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

Download history

daily snapshots · 106 days

▲ 3.0 M in the last 30 days (66.4%)

7.6 M1.1 M

Jul 28Sep 1Oct 6Nov 10

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": 7616440,
  "vram_estimates": [
    { "quant": "f8_e4m3", "gb": 861.7 }
  ],
  "updated_at": "2026-07-28T18:03:19Z"
}

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

Use via API

via OpenRouter · USD per 1M tokens · synced 2026-11-10

$0.26

input / 1M

$0.38

output / 1M

$0.13

cached input / 1M

$0.64

1M in + 1M out

Context window: 163,840 tokens
Max output: 147,456 tokens
Providers: 7
Cheapest provider: GMICloud · $0.21 / $0.31
Best throughput: —
AA Intelligence / Coding / Agentic: — / 44.2 / —

✓ Tool calling ✓ Reasoning ✓ Structured outputs ✗ Image input ✗ File input ✗ Audio input ✓ Prompt caching

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 any text-generation model

Popular comparisons

DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF 3.3 M DeepSeek-V4-Flash-0731 2.7 M GLM-5.3 2.0 M DeepSeek-R1 1.6 M DeepSeek-V3 1.5 M GLM-5 1.4 M

Appears in

Commercial-use text models