Boards / Raspberry Pi 5 + AI HAT+ 2
Pi 5 + AI HAT+ 2 (Hailo-10H): LLM benchmarks
A Hailo-10H NPU with its own 8GB RAM on a HAT, running Hailo-compiled models through hailo-ollama.
At a glance
- Measured runs18
- Models tested6
- Fastest run8.7 tok/s
- Llama 3.2 1B, Hailo-compiled, hailo-ollama · source ↗
- Sources5
Where to buy
- 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)
Every run on this board
| Model | Quant | Runtime | Gen tok/s | Prompt tok/s | TTFT ms | Source |
|---|---|---|---|---|---|---|
| Llama 3.2 1B | Hailo-compiled | hailo-ollama | 8.7 | – | – | source ↗ published 2026 |
| Qwen2.5-Coder 1.5B | Hailo-compiled | hailo-ollama | 8.06 | – | – | source ↗ 2026-01-20 |
| Qwen2 1.5B | Hailo-compiled | hailo-ollama | 8.03 | – | – | source ↗ tested 2026-01-25 |
| Qwen2.5-Coder 1.5B | Hailo-compiled | hailo-ollama | 7.94 | – | – | source ↗ tested 2026-01-25 |
| DeepSeek-R1-Distill-Qwen 1.5B | W4A8 | per M5Stack page | 7.05 | – | 660 | source ↗ accessed 2026-10-17 |
| DeepSeek-R1-Distill-Qwen 1.5B | Hailo-compiled | hailo-ollama | 6.83 | – | – | source ↗ tested 2026-01-25 |
| Qwen2.5 1.5B Instruct | W4A8 | per M5Stack page | 6.82 | – | 370 | source ↗ accessed 2026-10-17 |
| Qwen2.5 1.5B Instruct | Hailo-compiled | hailo-ollama | 6.76 | – | – | source ↗ tested 2026-01-25 |
| Qwen2.5 1.5B Instruct | Hailo-compiled | hailo-ollama | 6.74 | – | – | source ↗ 2026-01-20 |
| DeepSeek-R1-Distill-Qwen 1.5B | Hailo-compiled | hailo-ollama | 6.72 | – | – | source ↗ 2026-01-20 |
| Qwen2.5 1.5B Instruct | not reported | hailo-ollama | 6.34 | – | – | source ↗ 2026-04-24 |
| Qwen2 1.5B | Hailo-compiled | hailo-ollama | 5.89 | – | – | source ↗ 2026-01-20 |
| Qwen2.5 1.5B | not reported | hailo-ollama | 4.37 | – | – | source ↗ 2026-04-24 |
| Llama 3.2 3B | Hailo-compiled | hailo-ollama | 2.65 | – | – | source ↗ tested 2026-01-25 |
| Llama 3.2 3B | Hailo-compiled | hailo-ollama | 2.6 | – | – | source ↗ 2026-01-20 |
| Qwen2.5-Coder 1.5B | not reported | hailo-ollama | 2.07 | – | – | source ↗ 2026-04-24 |
| DeepSeek-R1-Distill-Qwen 1.5B | not reported | hailo-ollama | 1.53 | – | – | source ↗ 2026-04-24 |
| Llama 3.2 3B | not reported | hailo-ollama | 1.01 | – | – | source ↗ 2026-04-24 |
Can the Raspberry Pi 5 + AI HAT+ 2 run…
Can it run DeepSeek-R1-Distill-Qwen 1.5B?Can it run Llama 3.2 1B?Can it run Llama 3.2 3B?Can it run Qwen2 1.5B?Can it run Qwen2.5 1.5B?Can it run Qwen2.5-Coder 1.5B?
Have this board? Submit your own run →