ai-tier / edge

Llama 3.2 3B Instruct on Pi 5

Snapshot · ai-tier

Raspberry Pi 5 · 16 GB RAMAll performance measurements are for this device.

Capability shows how well the model answers the benchmark questions. Speed, response time and memory are measured on Raspberry Pi 5 · 16 GB.

Capability summarises instruction following, tool calling and finding information in long prompts. Speed and memory refer to the Raspberry Pi 5. — means unavailable.
ModelCapability / 100Output tok/sPrompt tok/sFirst token · sTask time · sPeak memory · MiBParameters · B
Llama 3.2 3B InstructQ4_K_M · 4,096 context · reasoning off775.928.914.870.44,4333.2

Benchmark breakdown

Instruction following · IFEvalTool calling · BFCLFinding information · RULER
707388

Test configuration

Model publisher
Meta
Model parameters
3.213 billion total
Published input support
text (metadata; not device validation)
Quantization
Q4_K_M
Context capacity
4,096 tokens
Reasoning mode
off
CPU threads / parallel requests
4 / 1
Temperature / seed
0 / 42
Measurement date
2026-10-19T12:51:05.961032+00:00
Result ID
split-8a67380bb030e73d511a
Runtime revision
620d2225cc436ab0b001e3200e590e3b286ef9ab
Artifact repository / revision
unsloth/Llama-3.2-3B-Instruct-GGUF / e7d0997e49c9cb00d88b4c1a6a16aa894b0bbc31
Artifact SHA256
6c99cc00ae910f6a532a80022cb4bc1939094527a089c29294b841c0bd87f74d
Dataset revision
a0fc00b6a07455d1efb70cc19d5ca94c5923c5261a0b41095083a41a1592a1f6
Configuration identity
2144c9b24e455ac0ba5935c2274d30d29864d0a21f801af9836e3f0a4cbca812

Measurement limits

Speed tests read 256 input tokens and generate 128 output tokens, repeated ten times. The output speed test starts without a long conversation history. Answer time uses six fixed prompts with up to 128 output tokens, repeated three times. First-text time is measured from the application making the request. Peak memory includes the loaded model; it excludes other applications on the device. Longer prompts may need more memory. Capability uses a fixed selection of public questions, rather than the full official benchmarks.

Measured 2026-10-19T12:51:05.961032+00:00.