Alibaba
Qwen3 30B A3B 2507 Instruct
Open weights
- Intelligence
- 7.5
- Rank 533 of 744 measured models
- Output speed
- 43.6 t/s
- Rank 346 of 403 measured models
- Price/1M
- $0.25
- Rank 189 of 659 measured models
- Context window
- 262K
- Rank 458 of 1199 measured models
Qwen3 30B A3B 2507 Instruct scores 7.5 on the Artificial Analysis Intelligence Index, ranking 533rd of 744 measured models. The closest models on this index are Devstral Small 2 (7.5), ERNIE 4.5 300B A47B (7.5), and Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) (7.5). At $0.25 per million tokens (3:1 input/output blended price), it is cheaper than ERNIE 4.5 300B A47B ($0.485). With an output speed of 43.6 t/s, it is slower than Devstral Small 2 (142 t/s).
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- Devstral Small 2
Mistral · — · 142 t/s
7.5—142 t/sCompare - ERNIE 4.5 300B A47B
Baidu · $0.485 · —
7.5$0.485—Compare - Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)
NVIDIA · — · —
7.5——Compare - Nous: Hermes 4 405B
Nous Research · $1.50 · —
7.5$1.50—Compare
