Verify critical details — pricing, licensing, availability — with the model's source before business decisions. Full methodology →
Qwen2.5-32B
Model family: qwen2-5
Qwen2.5's 32B general model, Apache 2.0 — the base for DeepSeek-R1-Distill-Qwen-32B (the standout o1-mini-class distill).
Listing Notes
Cataloged primarily as the base modelA model straight out of pretraining, before any fine-tuning for chat or specific tasks. Base models predict the next token but don't follow instructions well — they'll continue your prompt rather than respond to it. Most people never use base models directly; they use the instruct-tuned or chat versions built on top. Useful mostly for researchers and people doing their own fine-tuning. for DeepSeek-R1-Distill-Qwen-32B. A strong Qwen2.5 generalist under Apache 2.0, now a generation behind Qwen3.
Identity
- Creator
- Qwen
- Model family
- qwen2-5
- Release date
- 2024-09-18
Technical specs
- Parameter count
- 32B
- Context window
- 131K tokens
- Modalities
- Text
- Primary capabilities
- Chat
- Coding
- Instruction Following
- Long Context
- Multilingual
- Reasoning
License
- License
- Apache License 2.0
- Commercial use
- Allowed
- Terms
- Modification ✓
- Redistribution ✓
- Attribution ✓
Access
- Openness
- Open Weight
- Access methods
- Local Runtime Llama Cpp
- Local Runtime Ollama
- Local Runtime Vllm
- Weights Download Hf
- Cost tier
- Mixed
- llm
- open-weight
- commercial-friendly
- mid-size
- multilingual
- china-based
- apache-2-0
- base-model