ai-tier / edge

Ministral 3 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
Ministral 3 3B InstructQ4_K_M · 4,096 context · reasoning off515.526.919.2—4,6383.8

Benchmark breakdown

Instruction following · IFEvalTool calling · BFCLFinding information · RULER
568411

Test configuration

Model publisher
Mistral AI
Model parameters
3.849 billion total
Published input support
text, image (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
2026-10-18T06:02:33.168269+00:00
Result ID
split-1030ded09d7ed4b7508c
Runtime revision
620d2225cc436ab0b001e3200e590e3b286ef9ab
Artifact repository / revision
mistralai/Ministral-3-3B-Instruct-2512-GGUF / eb599d408350ea2bb60452cb86be7c7b2fc28227
Artifact SHA256
9ed150d4367e68df0ac8e1540f6ddc65b42d0ee26378329d1ecbca60f93fc5f8
Dataset revision
a0fc00b6a07455d1efb70cc19d5ca94c5923c5261a0b41095083a41a1592a1f6
Configuration identity
ce6022c8bb71c7303c1d2ca3fd406effef2e7d61e414560ae279194727d27c85

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 2026-10-18T06:02:33.168269+00:00.