Qwen3 VL 30B A3B Instruct
alibaba/qwen3-vl-30b-a3b-instruct- Alibaba
- Family · Qwen3 VL
- Released 3 Oct 2025
- Open weights
- Text · Image → Text
- Tools · JSON · Vision
Not on OSMEXO yet
Spec & list price
Context256K
Max output16K
Input / 1M$0.15
Output / 1M$0.604× input
Scores · standing
Intelligence7.9#307/490
Usage
Tokens / day6.7B▼ 11% 7d
Usage rank#104
Requests / day2.3M
Tool calls / req0.01
Per request · 30 days
Avg input1.8K0.1× median
Avg output1690.2× median
Cache hit1.6%0.0× median
Reasoning share0%0.0× median
Tool-call failures3.4%1.8× median
Consumption
Peak 6.8B 19 OctLow 854.6M 7 OctRank today #104
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
bar = share of the top score · Benchmark data: Artificial AnalysisSpeed · median across 3 providers, latest day
Output speed#321/33418 tok/s3.5× slower than median
Fastest provider24 tok/sbest of 3 providers
First token#2883.28 s3.0× longer than median
#13 cheapest of 41 with a similar score
Value
Intelligence Index
Blended price per 1M tokens (log)
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
- 441.3K · 627
Request parameters 17
- tools
- tool_choice
- response_format
- structured_outputs
- temperature
- top_p
- top_k
- min_p
- max_tokens
- stop
+7 more
- seed
- frequency_penalty
- logit_bias
- logprobs
- presence_penalty
- repetition_penalty
- top_logprobs
Interesting facts
- Less output room than similar models (16.4K against a 65.5K median).
- 2nd of 6 Qwen3 VL models by tokens last month.
When to use
Best for
- Image understanding in chat apps
- Document and screenshot extraction
- Structured JSON from images
- Self-hosted vision assistants
Think twice for
- Image generation
- Hardest visual reasoning tasks
- Autonomous coding agents
- Text-only bulk chat (cheaper options exist)
Research papers
Same family
Qwen3 VL- 9.9
- 13.4
- 9.5
- 8.4
- 11.9
- 7.0
- 8.2
Alternatives
other vendors · similar capability- 12.9
- 8.5
- 11.6
- 6.7
Want Qwen3 VL 30B A3B Instruct on OSMEXO?
Sign in to request it. Requests are reviewed; a request does not guarantee availability.