How we got this number
Each generated token reads the whole model from memory once: 19 GB. The Mac Studio M5 Ultra (256GB) moves 1228.8 GB/s, so the ceiling is 65 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 34B
| Mac Studio M5 Ultra (96GB) | 52 tok/s | Check price → |
| Mac Studio M5 Max (40-core GPU, 64GB) | 26 tok/s | Check price → |
| Mac mini M5 Pro (64GB) | 13 tok/s | Check price → |
| NVIDIA DGX Spark (128GB) | 10 tok/s | Check price → |
Other models on the Mac Studio M5 Ultra (256GB)
| ornith 1.5 9B | Fast | 120+ tok/s |
| Granite 4.2 8B | Fast | 120+ tok/s |
| Nemotron 3.5 lightning 30B (A3B) | Fast | 120+ tok/s |
| ornith 9B | Fast | 120+ tok/s |
| lfm 2.5 8B (A1B) | Fast | 120+ tok/s |
| minicpm v4.5 8B | Fast | 120+ tok/s |