M5Stack LLM8850 / Qwen2.5 1.5B
Can a M5Stack LLM8850 run Qwen2.5 1.5B?
Yes, at a comfortable chat speed. Measured generation speed: 15.06 tok/s across 1 public run.
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 LLM8850 M5Stack LLM8850 M.2 card (AX8850) | W4A16 | StackFlow | 15.06 | – | – | source ↗ accessed 2026-10-17 |
Qwen2.5 1.5B on other boards
- M5Stack AI Pyramid 16.77 tok/s best
- Rockchip RK3588 16.69 tok/s best
- Raspberry Pi 5 11.73 tok/s best
- Jetson Orin Nano Super 9.37 tok/s best
- Raspberry Pi 5 + AI HAT+ 2 6.82 tok/s best
- M5Stack Module LLM 4.63 tok/s best
Buy a M5Stack LLM8850
- M5Stack LLM8850 M.2 card (AX8850): price not verified yet Check price on Amazon
Ran Qwen2.5 1.5B on a M5Stack LLM8850? Submit your numbers →