Qwen3 30B A3B Instruct 2507
alibaba/qwen3-30b-a3b-instruct-2507- Alibaba
- Family · Qwen3
- Open weights
- Text → Text
- Tools · JSON
Not on OSMEXO yet
Spec & list price
Context256K
Max output236K
Input / 1M$0.10
Output / 1M$0.303× input
Usage
Tokens / day6.8B▲ 32% 7d
Usage rank#103
Requests / day5.0M
Tool calls / req0.02
Per request · 30 days
Avg input1.7K0.1× median
Avg output1580.2× median
Cache hit42%0.6× median
Tool-call failures5.7%3.0× median
Consumption
Peak 9.4B 8 OctLow 1.9B 24 OctRank today #103
News & trends
201 mentions this week ▲ 49%Qwen3 family · videos, posts, articles · 30 days
Trending · 14 days · Qwen3 family
- Qwen3.8 27b (Q6) casually breaking reCAPTCHA838 upvotes
- Memdoor: A team of 5 Qwen3.8-27B models beats Fable 5 on LiveCodeBench Hard416 points
- Neuron Explorer for Qwen3.5-4B: See every neuron at work, make targeted edits26 points
- New Card for Qwen3.8 27b and MiniMax H3656 upvotes
- Qwen 3.8 27B vs Strata Coder - Local LLM battle75.2K views
- DavidAU Qwen3.8 27B Turbo Brilliance 50X-Reasoning... tested - Local LLM setup87.7K views
News · latest from Qwen3
- Memdoor: A team of 5 Qwen3.8-27B models beats Fable 5 on LiveCodeBench Hardgithub.com · 31 Oct
- Neuron Explorer for Qwen3.5-4B: See every neuron at work, make targeted editsgithub.com · 26 Oct
- How to train your own Jev for $17Together AI · 23 Sep
Benchmarks
Benchmark data: Artificial AnalysisOutput speed#124/33477 tok/s1.2× faster than median
Fastest provider145 tok/sbest of 3 providers
First token#320.41 s2.6× quicker than median
Family progress
Intelligence Index
- Family releases33.7
Technical details
- Tokenizer
- Qwen3
- Knowledge cutoff
- 2025-06-30
- License
- Apache 2.0
- Parameters
- 30.5B
- Moderation
- none
- Downloads · likes
- 1.0M · 852
Request parameters 16
- tools
- tool_choice
- response_format
- structured_outputs
- temperature
- top_p
- top_k
- max_tokens
- stop
- seed
+6 more
- frequency_penalty
- logit_bias
- logprobs
- presence_penalty
- repetition_penalty
- top_logprobs
When to use
Best for
- Low-cost open-weight chat and drafting
- Structured extraction with JSON output
- Lightweight tool-calling agents
- Long document summarization on a budget
Think twice for
- Image or audio input (text-only)
- Hardest multi-step reasoning tasks
- Frontier-level coding agents
Research papers
Same family
Qwen3- 7.2
- 6.0
- 6.9
- 6.1
- 5.2
- 13.1
Want Qwen3 30B A3B Instruct 2507 on OSMEXO?
Sign in to request it. Requests are reviewed; a request does not guarantee availability.