Raspberry Pi 5 / Llama 3.2 3B

Can a Raspberry Pi 5 run Llama 3.2 3B?

Yes, usable but slower than reading speed. Measured generation speed: 0.14–5.95 tok/s across 6 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
1x Raspberry Pi 5 8GB
Q40distributed-llama v0.12.35.9514.3–source ↗
2025-02-15
Raspberry Pi 5
Raspberry Pi 5 / CM5
Ollama defaultOllama4.78––source ↗
2026-01-20
Raspberry Pi 5
Raspberry Pi 5
Q4_K_MOllama4.69––source ↗
accessed 2026-10-17
Raspberry Pi 5
Raspberry Pi 5 8GB
Ollama defaultOllama4.61––source ↗
2025-01-09
Raspberry Pi 5
Raspberry Pi 5 16GB
Ollama defaultOllama4.51––source ↗
2025-01-09
Raspberry Pi 5
Raspberry Pi 5 8GB
not reportedOllama0.14––source ↗
2026-04-24

Llama 3.2 3B on other boards

Buy a Raspberry Pi 5

Ran Llama 3.2 3B 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.