M3 Ultra (60-core GPU) — benchmark record
M3 Ultra (60-core GPU) local LLM benchmarks across 96 GB RAM tiers on Apple Silicon Mac. 1 published rows across 1 models with explicit evidence state and RAM-tier comparison. Peak published speed is 34.4 tok/s.
1Benchmark rows
1Models tested
1RAM configurations
34.4Fastest 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 — M3 Ultra (60-core GPU)
Sorted by avg tok/s descending. Click source badge to see original measurement.
| Chip (RAM) | Model | Quant | Avg tok/s | Runtime | Source |
|---|---|---|---|---|---|
| M3 Ultra (60-core GPU, 96 GB) | Qwen 2.5 14B | Q4_K - Medium | 34.4 tok/s | llamafile | ref |
Models tested on M3 Ultra (60-core GPU)
Data
benchmarks.json — full dataset · chips.json — chip summaries · benchmarks.csv — CSV export
Data from in-house lab measurements plus community-published benchmarks. See all chip families →