Qwen / text-generation updated 1 year ago

QwQ-32B

Name: QwQ-32B
Author: Qwen

QwQ is the reasoning model of the Qwen series. Compared with conventional instruction-tuned models, QwQ, which is capable of thinking and reasoning, can achieve significantly enhanced performance in downstream tasks, especially hard problems. QwQ-32B is the medium-sized reasoning model, which is capable of achieving competitive performance against state-of-the-art reasoning models, e.g., DeepSeek-R1, o1-mini.

Params

32.8 B

Context

40,960

Downloads 30d

318 K

Likes

2,959

Commercial use: allowed apache-2.0 Not gated SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

381 K318 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	bf16	65.5 GB	77.5 GB	❌ Won’t fit
model.safetensors (bf16, full)	bf16 + 40K ctx	65.5 GB	97.2 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/qwq-32b
{
  "hf_id": "Qwen/QwQ-32B",
  "params_b": 32.76,
  "context_length": 40960,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 318202,
  "vram_estimates": [
    { "quant": "bf16", "gb": 77.5 }
  ],
  "updated_at": "2026-07-28T18:06:00Z"
}

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

Specifications

Architecture: Qwen2ForCausalLM
Parameters: 32.8 B
Tensor type: BF16
Context length: 40,960
Vocabulary: 152,064
Layers / heads: 64 / 40
Licence: apache-2.0
First seen on the Hub: 2025-03-05
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Compare with

Qwen3-8B 16.3 M Qwen3.6-35B-A3B-NVFP4 11.3 M gpt-oss-20b 8.6 M Qwen3-32B 8.3 M dolphin-2.9.1-yi-1.5-34b 4.6 M OTel-2.0-LLM-31B-IT 3.3 M

Appears in

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