Boards Raspberry Pi 5 + AI HAT+ 2

Pi 5 + AI HAT+ 2 (Hailo-10H)

A Hailo-10H NPU with its own 8GB RAM on a HAT, running Hailo-compiled models through hailo-ollama.

Fastest run
8.7 tok/s
Measured runs
18
Models tested
6
Sources
5

Fastest: Llama 3.2 1B, Hailo-compiled, hailo-ollama · source ↗

Where to buy

Every run on this board

ModelSizeQuantRuntimeGen tok/sPrompt tok/sTTFT msSource
Llama 3.2 1B1BHailo-compiledhailo-ollama8.7––source ↗
published 2026
Qwen2.5-Coder 1.5B1.5BHailo-compiledhailo-ollama8.06––source ↗
2026-01-20
Qwen2 1.5B1.5BHailo-compiledhailo-ollama8.03––source ↗
tested 2026-01-25
Qwen2.5-Coder 1.5B1.5BHailo-compiledhailo-ollama7.94––source ↗
tested 2026-01-25
DeepSeek-R1-Distill-Qwen 1.5B1.5BW4A8per M5Stack page7.05–660source ↗
accessed 2026-10-17
DeepSeek-R1-Distill-Qwen 1.5B1.5BHailo-compiledhailo-ollama6.83––source ↗
tested 2026-01-25
Qwen2.5 1.5B Instruct1.5BW4A8per M5Stack page6.82–370source ↗
accessed 2026-10-17
Qwen2.5 1.5B Instruct1.5BHailo-compiledhailo-ollama6.76––source ↗
tested 2026-01-25
Qwen2.5 1.5B Instruct1.5BHailo-compiledhailo-ollama6.74––source ↗
2026-01-20
DeepSeek-R1-Distill-Qwen 1.5B1.5BHailo-compiledhailo-ollama6.72––source ↗
2026-01-20
Qwen2.5 1.5B Instruct1.5Bnot reportedhailo-ollama6.34––source ↗
2026-04-24
Qwen2 1.5B1.5BHailo-compiledhailo-ollama5.89––source ↗
2026-01-20
Qwen2.5 1.5B1.5Bnot reportedhailo-ollama4.37––source ↗
2026-04-24
Llama 3.2 3B3BHailo-compiledhailo-ollama2.65––source ↗
tested 2026-01-25
Llama 3.2 3B3BHailo-compiledhailo-ollama2.6––source ↗
2026-01-20
Qwen2.5-Coder 1.5B1.5Bnot reportedhailo-ollama2.07––source ↗
2026-04-24
DeepSeek-R1-Distill-Qwen 1.5B1.5Bnot reportedhailo-ollama1.53––source ↗
2026-04-24
Llama 3.2 3B3Bnot reportedhailo-ollama1.01––source ↗
2026-04-24

Can the Raspberry Pi 5 + AI HAT+ 2 run…

DeepSeek-R1-Distill-Qwen 1.5BLlama 3.2 1BLlama 3.2 3BQwen2 1.5BQwen2.5 1.5BQwen2.5-Coder 1.5B

Have this board? Submit your own run →

Get the monthly board report

New boards, new runtimes, new numbers. One email a month, no hype.