Qwen2.5 Coder 32B Instruct
alibaba/qwen-2.5-coder-32b-instruct- Alibaba
- Family · Qwen2 Coder
- Open weights
- Text → Text
Not on OSMEXO yet
Spec & list price
Context32K
Max output29K
Input / 1M$0.66
Output / 1M$1.001.5× input
Usage
Tokens / day8.2M▼ 31% 7d
Usage rank#397
Requests / day6.3K
Per request · 30 days
Avg input8120.1× median
Avg output1740.3× median
Consumption
Peak 30.1M 18 OctLow 3.4M 30 SepRank today #397
News & trends
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#285/33432 tok/s2.0× slower than median
First token#2381.87 s1.7× longer than median
Family progress
Intelligence Index
- Family releases6.7
Technical details
- Tokenizer
- Qwen
- Knowledge cutoff
- 2024-06-30
- License
- Apache 2.0
- Parameters
- 32.8B
- Moderation
- none
- Downloads · likes
- 532.5K · 2.2K
Request parameters 12
- response_format
- temperature
- top_p
- top_k
- min_p
- max_tokens
- stop
- seed
- frequency_penalty
- logit_bias
+2 more
- presence_penalty
- repetition_penalty
When to use
Best for
- Code completion and generation
- Self-hosted coding assistants
- Code explanation and refactoring in single files
Think twice for
- Agentic coding with tool calls
- Long codebase context
- Non-coding general chat
- Image understanding
Research papers
Same family
Qwen2 Coder- 6.7
- 5.8
Want Qwen2.5 Coder 32B Instruct on OSMEXO?
Sign in to request it. Requests are reviewed; a request does not guarantee availability.