Qwen3 VL 30B A3B is Alibaba's language model. A reasoning-focused vision-language MoE model with 30B total and 3B activated parameters, supporting deep visual perception and multimodal analysis.
Specifications
Canonical IDalibaba-qwen3-vl-30b-a3b-reasoning
TypeLanguage
StatusActive
CreatorAlibabaAlibaba
Input ModalitiesText
Output ModalitiesText
Parameters30B
Benchmarks
Intelligence Index
19.7
#224
Coding Index
13.1
#260
Math Index
82.3
#57
MMLU-Pro
0.8
#93
GPQA
0.7
#170
HLE
0.1
#158
LiveCodeBench
0.7
#63
IFBench
0.5
#171
Time to First Token
1.05s
#332
SciCode
0.3
#239
AIME 2025
0.8
#57
LCR
0.4
#167
TerminalBench Hard
0.1
#244
TAU2
0.2
#301
Output TPS

Capabilities

Input1/5
Text
Image·
Audio·
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
EAGLE Qwen 2.5 3B InstructAvailable
Qwen3.7 Max1.0M$1.25$3.75Available
Qwen3.6 Max Preview262K$1.04$6.24Available
Qwen3.6 27B262K$0.290$3.20Available
Qwen3.6 35B A3B262K$0.140$1.00Available
Qwen3.6 Plus1.0M$0.325$1.95Available
Qwen3 Max Thinking262K$0.780$3.90Available
Qwen3 Next 80B A3B128K$0.140$1.20Available
Qwen3 Max262K$0.359$1.43Available
Qwen3 Max Preview262K$1.20$6.00Available
Qwen3 VL 30B A3BCurrent

Model IDs