Qwen3-4B on Pi 5
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.
| Model | Capability / 100 | Output tok/s | Prompt tok/s | First token · s | Task time · s | Peak memory · MiB | Parameters · B |
|---|---|---|---|---|---|---|---|
| Qwen3-4BQ4_K_M · 4,096 context · reasoning off | 87 | 4.7 | 22.2 | 18.6 | 101.5 | 5,471 | 4 |
Benchmark breakdown
| Instruction following · IFEval | Tool calling · BFCL | Finding information · RULER |
|---|---|---|
| 78 | 82 | 100 |
Test configuration
- Model publisher
- Qwen
- Model parameters
- 4 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
- 2026-10-18T15:40:03.395347+00:00
- Result ID
- split-0abe1418dc701bf5fc16
- Runtime revision
- 620d2225cc436ab0b001e3200e590e3b286ef9ab
- Artifact repository / revision
- Qwen/Qwen3-4B-GGUF / bc640142c66e1fdd12af0bd68f40445458f3869b
- Artifact SHA256
- 7485fe6f11af29433bc51cab58009521f205840f5b4ae3a32fa7f92e8534fdf5
- Dataset revision
- a0fc00b6a07455d1efb70cc19d5ca94c5923c5261a0b41095083a41a1592a1f6
- Configuration identity
- 957d9778460002685045b4f66ea1cc7831642762afae11376b4b29f3671ac562
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 2026-10-18T15:40:03.395347+00:00.