Qwen3-30B-A3B
Active Parameters
30B
Context Length
131K
Modality
Text
Architecture
Mixture of Experts (MoE)
License
Apache 2.0
Release Date
29 Apr 2025
Knowledge Cutoff
Mar 2025
API Pricing (per 1M)
Input: $0.09 · Output: $0.30
System Requirements
VRAM requirements for different quantization methods and context sizes
1,024 tokens
Consumer
3x RTX 4090
24GB VRAM
Datacenter
1x NVIDIA A100
80GB VRAM
Apple Silicon
1x Apple M3 Max
128GB VRAM
131,072 tokens
Consumer
5x RTX 4090
24GB VRAM
Datacenter
2x NVIDIA A100
80GB VRAM
Apple Silicon
1x Apple M3 Max
128GB VRAM
Architecture Diagram
Evaluation Benchmarks
Rank
#150
| Benchmark | Score | Rank |
|---|---|---|
Software Engineering | 0.60 | 25 |
Graduate-Level QA | 0.658 | 91 |
Agentic Index | auto 0.9 | 119 |
General Text | 1382 | 127 |
Coding Index | 0.12 | 143 |
Intelligence Index | auto 0.08 Standard 0.07 | 282 302 |
Rankings
Overall Rank
#150
Coding Rank
#114
About Qwen3-30B-A3B
Qwen3-30B-A3B is an efficient Mixture-of-Experts model from Alibaba Cloud activating 3.3B parameters per token for high-throughput reasoning. It features dual thinking modes and multilingual fluency across 119 languages over a 131K context window.
Technical Specifications
Attention
Attention Structure
Grouped-Query Attention
Attention Heads
96
Key-Value Heads
8
Attention Head Dimension
128
Position Embedding
ROPE
RoPE Theta
1,000,000
Normalization
Layer Normalization
Activation Function
SwigLU
Dimensions
Hidden Dimension Size
4,096
Number of Layers
60
FFN Intermediate Size (Dense)
768
Tokenizer
Vocabulary Size
151,936
Mixture of Experts
Total Expert Parameters
3.0B
Number of Experts
128
Active Experts
8
FFN Intermediate Size (per Expert)
768
About Qwen 3
The Alibaba Qwen 3 model family comprises dense and Mixture-of-Experts (MoE) architectures, with parameter counts from 0.6B to 235B. Key innovations include a hybrid reasoning system, offering 'thinking' and 'non-thinking' modes for adaptive processing, and support for extensive context windows, enhancing efficiency and scalability.