Qwen3 30B A3B Instruct
Specifications
- Input
- Output
- Context window
- 262K tokens
- Veröffentlicht
- Jul 2025
Performance
- Speed
- 176 t/s
- TTFT
- 156 ms
- Latency
- 203 ms
- Intelligence
- —
Pricing
- Eingabe
- €0.10 per 1M tokens
- Ausgabe
- €0.30 per 1M tokens
Über dieses Modell
Qwen3 30B A3B Instruct is a compact Mixture-of-Experts model with 30B total parameters and 3B activated per token, offering excellent efficiency for general-purpose tasks. Features 262K native context with extension to 1M tokens, strong multilingual capabilities, and enhanced instruction following. Balances performance and computational efficiency with support for tool calling, code generation, and logical reasoning. Ideal for deployment scenarios requiring lower resource usage while maintaining quality across diverse task types.
Technische Daten
- Fähigkeiten
- Eingabe-Modalitäten
- Ausgabe-Modalitäten
- Reasoning
- No
Knowledge horizon
Veröffentlicht Jul 2025
Today
Since release 11 mo
See also
Modell zum Vergleich hinzufügen
Nach einem Modell suchen