Loading page content
QwQ-32BOpen
Tool use · Reasoning
Evaluation overview
Overall rank
#106
65 points · 180 models
Open-weight rank
#45
71.2 points · 109 models
Data coverage
102 items
2 sources · updated through 2026-07-16
Domain performance
Coding#94 / 160
67.6
Research#102 / 174
75.3
Agents#92 / 125
60.9
Evaluation highlights
All evaluationsBasic information
- Context (input / output)
- 131K / 33K
- Parameters
- 32.5B
- Release date
- 2025-03
- License
- Apache 2.0
- Input modalities
- Text
- Output modalities
- Text
- Training stages
- Pretraining + SFT + reinforcement learning
Availability
Ollama · Q4_K_MDeployment options
GGUF Q4_K_M · 24 GB VRAM
Related links
Version relationships
Qwq-32B family
QwQ-32B-Preview
2024-11 · Predecessor · Deprecated
QwQ-32BCurrent
2025-03 · Current model