Qwen2.5 3B Instruct on Pi 5

Snapshot 2026-10-27 · 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.
Model	Capability / 100	Output tok/s	Prompt tok/s	First token · s	Task time · s	Peak memory · MiB	Parameters · B
Qwen2.5 3B InstructQ4_K_M · 4,096 context · reasoning off	76	6	29.2	13.8	66.5	3,909	3.1

Benchmark breakdown

Instruction following · IFEval	Tool calling · BFCL	Finding information · RULER
58	79	92

Test configuration

Model publisher: Qwen
Model parameters: 3.086 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: 2026-10-19T14:47:58.213207+00:00
Result ID: split-d9148c9543203511b6cf
Runtime revision: 620d2225cc436ab0b001e3200e590e3b286ef9ab
Artifact repository / revision: Qwen/Qwen2.5-3B-Instruct-GGUF / 7dabda4d13d513e3e842b20f0d435c732f172cbe
Artifact SHA256: 626b4a6678b86442240e33df819e00132d3ba7dddfe1cdc4fbb18e0a9615c62d
Dataset revision: a0fc00b6a07455d1efb70cc19d5ca94c5923c5261a0b41095083a41a1592a1f6
Configuration identity: f8254fe10ce5b4b464af978e36a699324de98e0094d42d34c88c5ab0b83e7df6

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.

All Pi 5 measurements Methodology Publisher model card ↗Pinned engine source ↗

Measured 2026-10-19T14:47:58.213207+00:00.