Raspberry Pi 5 / Vinci Piccolo 1.0

Can a Raspberry Pi 5 run Vinci Piccolo 1.0?

Technically yes, but slowly. Measured generation speed: 2.95–3.21 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.

BoardQuantRuntimeGen tok/sPrompt tok/sTTFT msSource
Raspberry Pi 5
Raspberry Pi 5 (~15 GiB usable)
Q4_K_Mllama.cpp3.21––source ↗
2026-10-05
Raspberry Pi 5
Raspberry Pi 5 (~15 GiB usable)
Q4_K_Mllama.cpp3.19––source ↗
2026-10-05
Raspberry Pi 5
Raspberry Pi 5 (~15 GiB usable)
Q4_K_Mllama.cpp3––source ↗
2026-10-05
Raspberry Pi 5
Raspberry Pi 5 (~15 GiB usable)
Q4_K_Mllama.cpp2.95––source ↗
2026-10-05

Vinci Piccolo 1.0 on other boards

Buy a Raspberry Pi 5

Ran Vinci Piccolo 1.0 on a Raspberry Pi 5? Submit your numbers →

Get the monthly board report

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