Qwen3 30B A3B
Qwen3-30B-A3B is a smaller Mixture-of-Experts (MoE) model from Alibaba's Qwen3 series, containing 30.5 billion total parameters and 3.3 billion active parameters. The model features hybrid thinking/non-thinking modes, supports 119 languages, and has improved agent capabilities. It aims to surpass previous models like QwQ-32B while using significantly fewer active parameters.
Key Specifications
Parameters
30.5B
Context
128.0K
Release Date
April 29, 2025
Average Score
73.3%
Timeline
Key dates in the model's history
Announcement
April 29, 2025
Last Update
July 19, 2025
Today
October 5, 2026
Technical Specifications
Parameters
30.5B
Training Tokens
36.0T tokens
Knowledge Cutoff
-
Family
-
Capabilities
MultimodalZeroEval
Pricing & Availability
Input (per 1M tokens)
$0.10
Output (per 1M tokens)
$0.44
Max Input Tokens
128.0K
Max Output Tokens
128.0K
Supported Features
Function CallingStructured OutputCode ExecutionWeb SearchBatch InferenceFine-tuning
Benchmark Results
Model performance metrics across various tests and benchmarks
Reasoning
Logical reasoning and analysis
GPQA
Accuracy
AI: Accuracy • Self-reported
Other Tests
Specialized benchmarks
AIME 2024
Accuracy • Self-reported
AIME 2025
Accuracy • Self-reported
LiveBench
Accuracy • Self-reported
BFCL
v3 • Self-reported
LiveCodeBench
v5 • Self-reported
Arena Hard
Accuracy • Self-reported
Multi-IF
Accuracy • Self-reported
License & Metadata
License
apache_2_0
Announcement Date
April 29, 2025
Last Updated
July 19, 2025
Similar Models
All ModelsQwen2.5 32B Instruct
Alibaba
32.5B
Best score:0.9 (HumanEval)
Released:Sep 2024
QwQ-32B-Preview
Alibaba
32.5B
Best score:0.7 (GPQA)
Released:Nov 2024
Price:$1.20/1M tokens
QwQ-32B
Alibaba
32.5B
Best score:0.7 (GPQA)
Released:Mar 2025
Qwen2 72B Instruct
Alibaba
72.0B
Best score:0.9 (HumanEval)
Released:Jul 2024
Qwen2.5 72B Instruct
Alibaba
72.7B
Best score:0.9 (HumanEval)
Released:Sep 2024
Price:$1.20/1M tokens
Qwen2.5 14B Instruct
Alibaba
14.7B
Best score:0.8 (HumanEval)
Released:Sep 2024
Qwen3-Next-80B-A3B-Thinking
Alibaba
80.0B
Best score:0.8 (GPQA)
Released:Sep 2025
Price:$0.15/1M tokens
Qwen3 32B
Alibaba
32.8B
Released:Apr 2025
Price:$0.40/1M tokens
Recommendations are based on similarity of characteristics: developer organization, multimodality, parameter size, and benchmark performance. Choose a model to compare or go to the full catalog to browse all available AI models.