Apple · M3
Apple M3 Ultra
2025
Full Apple M3 Ultra benchmarks →
Apple M3 Ultra vs Apple M4 Max — Specs & Performance Compared
Side-by-side comparison of 2 CPU parts: Apple M3 Ultra vs Apple M4 Max. Release years: 2024, 2025. Specs, synthetic benchmarks, AI inference tok/s, and Amazon availability — click into any column header for the per-SKU benchmark page.
*Price sourced from Amazon.com. Last updated 2026-05-27. Price and availability subject to change.
Synthetic benchmarks
Higher is better. Per-row scores come from public benchmark databases (PassMark, TechPowerUp, Geekbench, Cinebench). Empty cells mean we don't yet have that benchmark on file for the SKU.
| Benchmark | Apple M3 Ultra | Apple M4 Max |
|---|---|---|
| Blender CPU | — | 475 points |
| Cinebench 2024 Multi-Core | — | 2,044 points |
| Cinebench 2024 Single-Core | — | 187 points |
| Cinebench R23 Multi-Core | — | 27,595 points |
| Cinebench R23 Single-Core | — | 2,209 points |
| Geekbench 6 Metal (GPU) | 259,668 points | — |
| Geekbench 6 Multi-Core | 27,759 points | 26,675 points |
| Geekbench 6 Multi-Core (avg) | — | 25,724 points |
| Geekbench 6 Single-Core | 3,201 points | 4,060 points |
| Geekbench 6 Single-Core (avg) | — | 3,916 points |
| PassMark CPU Mark | 72,769 pts | 44,002 points |
| PassMark CPU Mark Single Thread | 5,048 points | — |
AI inference (tokens/sec)
Top community-reported tokens-per-second results for popular LLMs. See the per-SKU benchmark page for the full set including quantization, prompt length, and source citations.
Apple M3 Ultra
- deepseekr1:32b: 100.0 tok/s
- qwen3:235b: 31.9 tok/s
- qwen3:0.6b: 31.0 tok/s
Apple M4 Max
- llama3.1:8b: 1000.0 tok/s
- Llama 3 8B: 64.0 tok/s
- Mistral 7B: 55.0 tok/s