M3 Ultra (60-core GPU, 96 GB) — LLM Benchmarks
Measured LLM inference benchmarks for M3 Ultra (60-core GPU, 96 GB). Tokens per second across 1 models and multiple quantizations. Real runs, not estimates.
1Benchmark rows
1Models tested
34.4Fastest avg tok/s (Qwen 2.5 14B Instruct)
0Factory-lab verified rows
Benchmark results for M3 Ultra (60-core GPU, 96 GB)
Rows sorted by avg tok/s descending. Click source badge to see original measurement page.
| Model | Quant | Avg tok/s | Runtime | Source |
|---|---|---|---|---|
| Qwen 2.5 14B Instruct | Q4_K - Medium | 34.4 tok/s | — | ref |
Models tested on this chip
Data
benchmarks.json — full dataset · chips.json — chip summaries · benchmarks.csv — CSV export
Data sourced from factory lab measurements and community reference runs. See all chips →