Benchmarking Qwen2.5 Local LLM Sizes in n8n on Apple Silicon

Description and use

Benchmarking five Qwen2.5 sizes in n8n on an M2 Mac revealed that 1.5B and 3B models deliver faster and more accurate results than the recommended 14B, especially for classification, extraction, and tool‑calling workflows.

Problem

Choosing the right LLM size for n8n workflows on an M2 Mac can lead to significant latency and accuracy trade‑offs.

Outcome

The 1.5B model outperformed the 14B on tool‑calling accuracy and speed, while the 3B model matched or exceeded 14B on extraction. 7B was slower and no better in accuracy. 0.5B was fast but too inaccurate for production routing.

Workflow

• 1. Pull five Qwen2.5 models via Ollama
• 2. Set up n8n in Docker on the same Mac
• 3. Create five n8n workflows (classification, extraction, summarization, RAG Q&A, tool‑calling)
• 4. Run each workflow 5 times with each model size
• 5. Record wall‑time and accuracy metrics
• 6. Analyze results and recommend model sizes

Evidence

The 1.5B model beat the 14B on tool‑calling accuracy AND speed

Source

The 7B is the worst pick. It’s slow (4‑9s) and its accuracy is identical to or worse than 3B

Source