M5Stack Module LLM / Qwen2.5 0.5B
Can a M5Stack Module LLM run Qwen2.5 0.5B?
Yes, at a comfortable chat speed. Measured generation speed: 10.32–12.52 tok/s across 2 public runs.
Rule of thumb: 10+ tok/s feels like a chat; 4–10 is usable for assistants and automations; under 4 is batch-job territory. Speeds depend on quantization, runtime, context length and cooling. Check each source.
| Board | Quant | Runtime | Gen tok/s | Prompt tok/s | TTFT ms | Source |
|---|---|---|---|---|---|---|
| M5Stack Module LLM M5Stack Module LLM / LLM630 (AX630C) | W4A16 | StackFlow | 12.52 | – | 442.95 | source ↗ accessed 2026-10-17 |
| M5Stack Module LLM M5Stack Module LLM / LLM630 (AX630C) | W8A16 | StackFlow | 10.32 | – | 359.8 | source ↗ accessed 2026-10-17 |
Qwen2.5 0.5B on other boards
- M5Stack AI Pyramid 37.11 tok/s best
- M5Stack LLM8850 27.05 tok/s best
- Jetson Orin Nano Super 13.31 tok/s best
- Raspberry Pi 5 1.54 tok/s best
Buy a M5Stack Module LLM
- M5Stack LLM Module Kit (AX630C): $79.9 regular price; out of stock when checked, source ↗ (2026-10-17) Check price (affiliate slot)
- M5Stack Module LLM (as tested in paper): $99.9 price quoted in arXiv paper, source ↗ (2026-04-24) Check price (affiliate slot)
Ran Qwen2.5 0.5B on a M5Stack Module LLM? Submit your numbers →