Qwen3 32B
Specifications
- Input
- Output
- Context window
- 33K tokens
- Released
- Apr 2025
Performance
- Speed
- 23 t/s
- TTFT
- 241 ms
- Latency
- —
- Intelligence
- —
Pricing
- Input
- €0.09 per 1M tokens
- Output
- €0.25 per 1M tokens
About this model
Qwen3 32B is a base foundation model with 32 billion parameters and 262K native context, designed for fine-tuning and custom adaptations. Pre-trained on diverse multilingual data covering 77.5% of languages, providing strong general capabilities across text understanding, code, mathematics, and reasoning. Serves as the foundation for specialized models and custom fine-tuning projects requiring a powerful mid-sized base. Ideal starting point for domain-specific adaptations and research applications.
Technical specifications
- Capabilities
- Input modalities
- Output modalities
- Reasoning
- Hybrid Default off
Knowledge horizon
Knowledge cutoff Mar 2024
Released Apr 2025
Today
Training to release 13 mo Since release 13 mo
See also
Add Model to Comparison
Search for a model to add