Qwen3 Coder 30B A3B Instruct
alibaba/qwen3-coder-30b-a3b-instruct- Alibaba
- Family · Qwen3 Coder
- Released 31 Jul 2025
- Open weights
- Text → Text
- Tools · JSON
Not on OSMEXO yet
Spec & list price
Context256K
Max output236K
Input / 1M$0.07
Output / 1M$0.284× input
Scores · standing
Intelligence9.6#255/489
Usage
Tokens / day1.6B▼ 12% 7d
Usage rank#168
Requests / day207.3K
Tool calls / req0.28
Per request · 30 days
Avg input7.4K0.5× median
Avg output2420.4× median
Cache hit63%about median
Tool-call failures3.5%1.8× median
Consumption
Peak 2.4B 21 OctLow 393.8M 22 OctRank today #168
News & trends
7 mentions this week ▲ 133%Qwen3 Coder family · videos, posts, articles · 30 days
Trending · 14 days · Qwen3 Coder family
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
- Running Qwen3.8-Flash-Next NVFP4 at 184 tok/s on a single RTX 6000 Promeshapplied.com · 26 Oct
Benchmarks
bar = share of the top score · Benchmark data: Artificial AnalysisSpeed · median across 2 providers, latest day
Output speed#201/33356 tok/s1.2× slower than median
Fastest provider90 tok/sbest of 2 providers
First token#1410.85 s1.2× quicker than median
#6 cheapest of 42 with a similar score
Value
Intelligence Index
Blended price per 1M tokens (log)
Family progress
Intelligence Index
- Family releases9.6
Technical details
- Tokenizer
- Qwen3
- Knowledge cutoff
- 2025-06-30
- License
- Apache 2.0
- Parameters
- 30.5B
- Moderation
- none
- Downloads · likes
- 1.0M · 1.3K
Request parameters 10
- tools
- tool_choice
- response_format
- structured_outputs
- temperature
- top_p
- top_k
- max_tokens
- stop
- frequency_penalty
Interesting facts
- 2.6× the output room of similar models (235.9K against a 91.7K median).
- Released 458 days ago, the newest of 2 Qwen3 Coder models.
When to use
Best for
- Self-hosted coding assistants
- Code generation with very large outputs
- Repository-level code questions
- Low-cost code review and refactoring
Think twice for
- Hardest autonomous coding agents
- Image understanding
- Math-heavy reasoning
- Non-coding general chat
Research papers
Same family
Qwen3 Coder- 11.9
Alternatives
other vendors · similar capability- 12.9
- 8.5
- 10.0
- 6.7
Want Qwen3 Coder 30B A3B Instruct on OSMEXO?
Sign in to request it. Requests are reviewed; a request does not guarantee availability.