Qwen2.5 0.5B Instruct
About
Instruction-tuned 0.5B variant of Qwen-2.5 for efficient on-device deployment. Balanced for speed and responsiveness on resource-constrained hardware.
Capabilities
VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode Execution
Providers(1)
| Provider | Input (per 1M) | Output (per 1M) | Type | |
|---|---|---|---|---|
| Fireworks AI | $0.1 | $0.1 | Serverless |
Benchmark Scores(4)
| Benchmark | Score | Version | Source |
|---|---|---|---|
| Google-Proof Q&A | 28.9 | diamond | Open LLM Leaderboard |
| HellaSwag | 81.4 | 10-shot | Open LLM Leaderboard |
| HumanEval | 35.6 | pass@1 | Open LLM Leaderboard |
| Massive Multitask Language Understanding | 54.2 | 5-shot | Open LLM Leaderboard |
