M5 Pro — benchmark record
M5 Pro local LLM benchmarks across 64 GB RAM tiers on Apple Silicon Mac. 4 published rows across 4 models with explicit evidence state and RAM-tier comparison. Peak published speed is 41.9 tok/s.
4Benchmark rows
4Models tested
1RAM configurations
41.9Fastest avg tok/s
RAM configurations
Each configuration differs only in unified memory. More RAM = larger models fit. Throughput is similar across RAM tiers at the same model size.
All benchmark rows — M5 Pro
Sorted by avg tok/s descending. Click source badge to see original measurement.
| Chip (RAM) | Model | Quant | Avg tok/s | Runtime | Source |
|---|---|---|---|---|---|
| M5 Pro (64 GB) | Qwen3.5-35B-A3B | Q4_K_L | 41.9 tok/s | llama.cpp | ref |
| M5 Pro (64 GB) | Qwen3.5-9B | Q4_K - Medium | 25.0 tok/s | llama.cpp | ref |
| M5 Pro (64 GB) | Qwen3.5-122B-A10B | IQ1_M | 18.0 tok/s | llama.cpp | ref |
| M5 Pro (64 GB) | Qwen3.5-27B | Q4_K - Medium | 10.0 tok/s | llama.cpp | ref |
Models tested on M5 Pro
Data
benchmarks.json — full dataset · chips.json — chip summaries · benchmarks.csv — CSV export
Data sourced from Silicon Score Lab measurements and community reference runs. See all chip families →