Can a Raspberry Pi 5 + AI HAT+ 2 run DeepSeek-R1-Distill-Qwen 1.5B?
Yes, usable but slower than reading speed. Measured generation speed: 1.53–7.05 tok/s across 4 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 | Size | Runtime | Gen tok/s | Source |
|---|---|---|---|---|
| Raspberry Pi 5 + AI HAT+ 2 Hailo-10H (host not stated) | 1.5B | per M5Stack page | 7.05 | source ↗ accessed 2026-10-17 |
| Raspberry Pi 5 + AI HAT+ 2 Raspberry Pi 5 8GB + AI HAT+ 2 | 1.5B | hailo-ollama | 6.83 | source ↗ tested 2026-01-25 |
| Raspberry Pi 5 + AI HAT+ 2 | 1.5B | hailo-ollama | 6.72 | source ↗ 2026-01-20 |
| Raspberry Pi 5 + AI HAT+ 2 | 1.5B | hailo-ollama | 1.53 | source ↗ 2026-04-24 |
DeepSeek-R1-Distill-Qwen 1.5B on other boards
- M5Stack LLM8850 13.29 tok/s best
- Rockchip RK3588 11.5 tok/s best
- Jetson Orin Nano Super 9.59 tok/s best
- Raspberry Pi 5 9.04 tok/s best
- M5Stack Module LLM 3.57 tok/s best
Buy a Raspberry Pi 5 + AI HAT+ 2
- Raspberry Pi AI HAT+ 2 (add-on, needs a Pi 5)$180official list price after Apr 2026 increase (launched at $130) · price source ↗ (2026-04-01)Buy at Seeed StudioBuy on Amazon
- Raspberry Pi 5 + AI HAT+ 2 (as tested in paper)$451.83price quoted in arXiv paper · price source ↗ (2026-04-24)Buy at Seeed StudioBuy on Amazon
Ran DeepSeek-R1-Distill-Qwen 1.5B on a Raspberry Pi 5 + AI HAT+ 2? Submit your numbers →