Qwen 3 VL 30B A3B Instruct
Qwen builds the Qwen 3 VL 30B A 3B Instruct model, a chat model capable of function calling, JSON mode, reasoning, streaming, text generation, and vision, with a notable context window of 262,144 tokens. It excels in multimodal reasoning, particularly in STEM and math, with capabilities such as causal analysis and logical, evidence-based answers.
Input
Output
Context
262K
Max Output
33K
Parameters
30B
Technical Specifications
Model TypeChat
Context Window262,144 tokens
Max Output Tokens32,768 tokens
Parameters30B
Release DateSep 30, 2025
Training CutoffMar 1, 2025
Licenseapache-2.0
Open SourceYes
Input Modalities
TextImage
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
6.4%
HLE
69.5%
GPQA
30.8%
SciCode
76.4%
MMLU Pro
72.3
Math
14.3
Coding
47.6%
LiveCodeBench
10.0
Intelligence
124
Speed (tok/s)
1.1
TTFA (s)
1.1
TTFT (s)
Resources & Links
Estimated GPU Requirements for Qwen 3 VL 30B A3B Instruct
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 24, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.