M5Stack LLM8850 / Qwen3 0.6B
Can a M5Stack LLM8850 run Qwen3 0.6B?
Yes, at a comfortable chat speed. Measured generation speed: 12.88 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) | W8A16 | StackFlow | 12.88 | – | 670.51 | source ↗ accessed 2026-10-17 |
Qwen3 0.6B on other boards
- Rockchip RK3588 32.91 tok/s best
- Rockchip RK3576 24.85 tok/s best
- M5Stack Module LLM 10.28 tok/s best
Buy a M5Stack LLM8850
- M5Stack LLM8850 M.2 card (AX8850): price not verified yet Check price (affiliate slot)
Ran Qwen3 0.6B on a M5Stack LLM8850? Submit your numbers →