Qwen3 32B

Tool callingStructured outputReasoning

Hugging Face Launch post Website Docs

Dense open Qwen model for self-hosted chat, reasoning, and coding

Context: 131K
Released: 1y ago
Parameters: 32B
Input / 1M tokens: $0.08
Output / 1M tokens: $0.28

Sources:models.devOpenRouter

Benchmarks

DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.

Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.

Other published benchmarks

Evaluation	Reported score and source
GPQA diamond	65.7% Epoch AI · Qwen3-32B Epoch AI evaluation
GPQA diamond	54.1% Epoch AI · Qwen3-32B_none Reasoning effort: none Epoch AI evaluation
OTIS Mock AIME 2024-2025	66.9% Epoch AI · Qwen3-32B Epoch AI evaluation
OTIS Mock AIME 2024-2025	23.1% Epoch AI · Qwen3-32B_none Reasoning effort: none Epoch AI evaluation

Benchmark compilation: Epoch AI, Capabilities & benchmarking (CC BY attribution). Scores are converted to percentages and model names matched to the Vertical Tabs catalog. Individual evaluations are credited to their original sources. External results may carry separate licences and evaluation configurations; do not interpret scores from different harnesses as directly comparable.

Specifications

Developer: Qwen
Model family: Qwen
Type: Language model
Predecessor: —
Successor: —
Released: April 1, 2025
Model ID: qwen/qwen3-32b
Openness: Open weights
License: —
Parameters: 32B
Input modalities: text
Output modalities: text
Modality: text->text
Native context: 256K
Tokenizer: Qwen3
Max output tokens: 16K
Knowledge cutoff: 2025-04
Hugging Face: Qwen/Qwen3-32B
Source freshness: Metadata synced Oct 8, 2026, 10:17 PM UTC

Additional source evidence

Source model: alibaba/qwen3-32b
Source family: qwen
Last updated: 2025-04
Knowledge cutoff: 2025-04
Model context: 131K
Model output limit: 16K
Open weights: Yes
File attachments: No
Reasoning: Yes
Tool calling: Yes
Temperature control: Yes

Downloadable weights

Hugging Face

Published benchmarks

Benchmark	Score	Evaluation details	Evidence
Aider Polyglot	40 · percent correct	2025-05-08	Source

Complete source record (JSON)

{
  "id": "alibaba/qwen3-32b",
  "name": "Qwen3 32B",
  "description": "Dense open Qwen model for self-hosted chat, reasoning, and coding",
  "family": "qwen",
  "last_updated": "2025-04",
  "knowledge": "2025-04",
  "attachment": false,
  "reasoning": true,
  "tool_call": true,
  "temperature": true,
  "modalities": {
    "input": [
      "text"
    ],
    "output": [
      "text"
    ]
  },
  "limit": {
    "context": 131072,
    "output": 16384
  },
  "benchmarks": [
    {
      "name": "Aider Polyglot",
      "score": 40,
      "source": "https://aider.chat/docs/leaderboards/",
      "metric": "percent correct",
      "date": "2025-05-08"
    }
  ],
  "release_date": "2025-04",
  "open_weights": true,
  "weights": [
    {
      "label": "Hugging Face",
      "url": "https://huggingface.co/Qwen/Qwen3-32B"
    }
  ]
}

Infrastructure

Provider availability

All providers

Provider	Endpoint	Context	Input /M tokens	Output /M tokens	Cached input /M tokens	Cache write /M tokens	Uptime 1d	Data handling
DeepInfra	deepinfra/fp8	41K	$0.08	$0.28	—	—	98.96%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
SiliconFlow	siliconflow/fp8	131K	$0.14	$0.57	—	—	99.46%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Tenstorrent	tenstorrent/fp8	20K	$0.14	$0.40	$0.09	—	99.36%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15

Provider data:OpenRouter

Deployment graph

Can I run this?

Vertical Tabs only shows compatibility when it has structured evidence tying this exact model to hardware, runtime, quantization, memory use, and observed performance.

Browse hardware