Qwen3 VL 30B A3B
alibaba/qwen3-vl-30b-a3b-thinking- Alibaba
- Family · Qwen3 VL
- Open weights
- Text · Image → Text
- Tools · JSON · Vision
Not on OSMEXO yet
Spec & list price
Context256K
Max output236K
Input / 1M$0.29
Output / 1M$1.003.4× input
Usage
Tokens / day3.5M▼ 36% 7d
Usage rank#429
Requests / day1.2K
Tool calls / req0.05
Per request · 30 days
Avg input2.5K0.2× median
Avg output1.3K1.9× median
Reasoning share88%1.6× median
Tool-call failures8.5%4.5× median
Consumption
Peak 45.7M 1 OctLow 3.1M 17 OctRank today #429
News & trends
1 mentions this week ▼ 50%Qwen3 VL family · videos, posts, articles · 30 days
Trending · 14 days · Qwen3 VL family
- FLUX.3 Image Klein (5.6B + Qwen3-VL-4B-Instruct) across 15 complex prompts: Macro, Typography, Fluid physics, and 0.5x Selfies, Workflows Include5 upvotes
- FLUX.3 Image Klein (5.6B + Qwen3-VL-4B-Instruct) across 15 complex prompts: Macro, Typography, Fluid physics, and 0.5x Selfies, Workflows Include5 upvotes
News · latest from Alibaba
- Memdoor: A team of 5 Qwen3.8-27B models beats Fable 5 on LiveCodeBench Hardgithub.com · 31 Oct
- Qwen3.8-Flash Now Available in the EU on Alibaba Cloudtwitter.com · 31 Oct
- Alibaba's Qwen3.8-Flash-Next model tried to upload a file to Beijing in a testnotebookcheck.net · 27 Oct
- Neuron Explorer for Qwen3.5-4B: See every neuron at work, make targeted editsgithub.com · 26 Oct
Benchmarks
Benchmark data: Artificial AnalysisOutput speed#247/33442 tok/s1.5× slower than median
First token#1941.3 s1.2× longer than median
Family progress
Intelligence Index
- Family releases11.9
Technical details
- Tokenizer
- Qwen3
- Knowledge cutoff
- 2025-03-31
- License
- Apache 2.0
- Parameters
- 31.1B
- Moderation
- none
- Downloads · likes
- 16.1K · 208
Request parameters 11
- tools
- tool_choice
- response_format
- structured_outputs
- reasoning
- include_reasoning
- temperature
- top_p
- top_k
- max_tokens
+1 more
- frequency_penalty
When to use
Best for
- Chart and document image question answering
- Self-hosted multimodal assistants (open weights)
- Visual reasoning that benefits from step-by-step thinking
- Tool-calling agents that read screenshots
- Long multimodal conversations with large context
Think twice for
- Latency-sensitive simple chat
- Image generation
- Video or audio input
- Frontier-level coding agents
Research papers
Same family
Qwen3 VL- 9.9
- 13.4
- 9.5
- 8.4
- 11.9
- 7.0
- 8.2
Want Qwen3 VL 30B A3B on OSMEXO?
Sign in to request it. Requests are reviewed; a request does not guarantee availability.