Qwen·released 2024-09-171 source
Not yet benchmarked
Claims drawn from cited facts, not live model generation.
Developed by Qwen and released in 2024, this model has 3.09 billion parameters, placing it at the compact end of the scale, which implies greater efficiency and lower cost but less headroom than frontier-scale models.
3 cited facts
This model is not yet benchmarked on any tracked benchmarks.
1 cited fact
The model does not hold the top score on any benchmark, with no top scores held, meaning it has no genuine category leadership.
1 cited fact
2 facts cross-checked across data sources: 2 single-source.
Source facts, citations, and refresh stamp for this record.
Sources: huggingface_models
Qwen2.5-3B-Instruct is an AI model developed by Qwen, released 2024-09-17. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.