Qwen3 30B A3B

Tool callingStructured outputReasoning

Hugging Face Launch post Website Docs

Sparse MoE Qwen model with 3B active parameters for efficient chat and reasoning

Context: 41K
Released: 1y ago
Parameters: 30B
Input / 1M tokens: $0.12
Output / 1M tokens: $0.50

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	61.7% Epoch AI · Qwen3-30B-A3B Epoch AI evaluation
GPQA diamond	50.4% Epoch AI · Qwen3-30B-A3B_none Reasoning effort: none Epoch AI evaluation
OTIS Mock AIME 2024-2025	62.8% Epoch AI · Qwen3-30B-A3B Epoch AI evaluation
OTIS Mock AIME 2024-2025	25.6% Epoch AI · Qwen3-30B-A3B_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 28, 2025
Model ID: qwen/qwen3-30b-a3b
Openness: Open weights
License: —
Parameters: 30B
Input modalities: text
Output modalities: text
Modality: text->text
Native context: 256K
Tokenizer: Qwen3
Max output tokens: 16K
Knowledge cutoff: 2025-03-31
Hugging Face: Qwen/Qwen3-30B-A3B
Source freshness: Metadata synced Oct 8, 2026, 10:17 PM UTC

Additional source evidence

Source model: alibaba/qwen3-30b-a3b
Source family: qwen
Last updated: 2025-04-28
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

Complete source record (JSON)

{
  "id": "alibaba/qwen3-30b-a3b",
  "name": "Qwen3 30B A3B",
  "description": "Sparse MoE Qwen model with 3B active parameters for efficient chat and reasoning",
  "family": "qwen",
  "last_updated": "2025-04-28",
  "attachment": false,
  "reasoning": true,
  "tool_call": true,
  "temperature": true,
  "modalities": {
    "input": [
      "text"
    ],
    "output": [
      "text"
    ]
  },
  "limit": {
    "context": 131072,
    "output": 16384
  },
  "release_date": "2025-04-28",
  "open_weights": true,
  "weights": [
    {
      "label": "Hugging Face",
      "url": "https://huggingface.co/Qwen/Qwen3-30B-A3B"
    }
  ]
}

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	$0.12	$0.50	—	—	100.00%	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