M5 vs M3
Side-by-side LLM inference benchmarks: M5 versus M3 across 3 models. Evidence-backed tok/s measurements with confidence metadata.
3Shared models
M5Wins 3 of 3
66%Avg speed advantage
6Measurements used
M5 is faster in 3 of 3 models tested. Average advantage: 66%.
Model-by-model comparison
Each row shows the fastest published generation speed for that model on each chip family. Higher tok/s is better. Evidence badges show data provenance.
| Model | M5 | M3 |
|---|---|---|
| llama-3-1-8b-instruct | 22.3 tok/s Q4_K_M | 13.5 tok/s Q4_K_M |
| llama-3-2-1b-instruct | 98.4 tok/s Q4_K_M | 67.2 tok/s Q4_K_M |
| qwen-2-5-14b-instruct | 11.5 tok/s Q4_K_M | 6.1 tok/s Q4_K_M |
Data confidence
This comparison uses 6 measurements. 6 are community-reported.
All numbers reflect generation speed (tok/s) at the best available quantization for each side. Quantization levels may differ between families. Where quant levels differ, the comparison shows each chip at its measured best — not a controlled variable.
Chip variants in this comparison
Data
benchmarks.json — full dataset · benchmarks.csv — CSV export