How we got this number
Each generated token reads the whole model from memory once: 39 GB. The Mac Studio M5 Ultra (96GB) moves 1228.8 GB/s, so the ceiling is 32 tokens/sec. Real machines reach a fraction of that ceiling; we use 80%, calibrated against a measured Mac run. Send us your real numbers and we'll replace the estimate.
Faster machines for Code Llama 70B
| Mac Studio M5 Ultra (256GB) | 25 tok/s | Check price → |
| Mac Studio M5 Max (40-core GPU, 64GB) | 13 tok/s | Check price → |
| Mac mini M5 Pro (64GB) | 6.3 tok/s | Check price → |
| NVIDIA DGX Spark (128GB) | 4.9 tok/s | Check price → |
Other models on the Mac Studio M5 Ultra (96GB)
| Nemotron 3.5 lightning 30B (A3B) | Fast | 120+ tok/s |
| Gemma 3 12B | Fast | 120+ tok/s |
| Qwen 3 30B (A3B) | Fast | 120+ tok/s |
| Gemma 4 26B (A4B) | Fast | 120+ tok/s |
| Qwen3.5 35B (A3B) | Fast | 120+ tok/s |
| Phi 3 14B | Fast | 120+ tok/s |