Raspberry Pi 5 + AI HAT+ 2 / Qwen2.5 1.5B
Can a Raspberry Pi 5 + AI HAT+ 2 run Qwen2.5 1.5B?
Yes, usable but slower than reading speed. Measured generation speed: 4.37–6.82 tok/s across 5 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 |
|---|---|---|---|---|---|---|
| Raspberry Pi 5 + AI HAT+ 2 Hailo-10H (host not stated) | W4A8 | per M5Stack page | 6.82 | – | 370 | source ↗ accessed 2026-10-17 |
| Raspberry Pi 5 + AI HAT+ 2 Raspberry Pi 5 8GB + AI HAT+ 2 | Hailo-compiled | hailo-ollama | 6.76 | – | – | source ↗ tested 2026-01-25 |
| Raspberry Pi 5 + AI HAT+ 2 Raspberry Pi 5 + AI HAT+ 2 | Hailo-compiled | hailo-ollama | 6.74 | – | – | source ↗ 2026-01-20 |
| Raspberry Pi 5 + AI HAT+ 2 Raspberry Pi 5 + AI HAT+ 2 | not reported | hailo-ollama | 6.34 | – | – | source ↗ 2026-04-24 |
| Raspberry Pi 5 + AI HAT+ 2 Raspberry Pi 5 + AI HAT+ 2 | not reported | hailo-ollama | 4.37 | – | – | source ↗ 2026-04-24 |
Qwen2.5 1.5B on other boards
- M5Stack AI Pyramid 16.77 tok/s best
- Rockchip RK3588 16.69 tok/s best
- M5Stack LLM8850 15.06 tok/s best
- Raspberry Pi 5 11.73 tok/s best
- Jetson Orin Nano Super 9.37 tok/s best
- M5Stack Module LLM 4.63 tok/s best
Buy a Raspberry Pi 5 + AI HAT+ 2
- Raspberry Pi AI HAT+ 2 (add-on, needs a Pi 5): $180 official list price after Apr 2026 increase (launched at $130), source ↗ (2026-04-01) Check price (affiliate slot)
- Raspberry Pi 5 + AI HAT+ 2 (as tested in paper): $451.83 price quoted in arXiv paper, source ↗ (2026-04-24) Check price (affiliate slot)
Ran Qwen2.5 1.5B on a Raspberry Pi 5 + AI HAT+ 2? Submit your numbers →