How we got this number
Each generated token reads the whole model from memory once: 8.2 GB. The NVIDIA DGX Spark (128GB) moves 273 GB/s, so the ceiling is 33 tokens/sec. Real machines reach a fraction of that ceiling; we use 70%, an assumption until we get measured runs for this kind of machine. Send us your real numbers and we'll replace the estimate.
Faster machines for Qwen 14B
| Mac Studio M5 Ultra (96GB) | 120 tok/s | Check price → |
| Mac Studio M5 Ultra (256GB) | 120 tok/s | Check price → |
| Mac Studio M5 Max (40-core GPU, 64GB) | 60 tok/s | Check price → |
| Mac mini M5 Pro (24GB) | 30 tok/s | Check price → |
Other models on the NVIDIA DGX Spark (128GB)
| lfm 2.5 8B (A1B) | Fast | 120+ tok/s |
| Gemma 2B | Fast | 112 tok/s |
| smollm 2 1.7B | Fast | 106 tok/s |
| starCoder 2 3B | Fast | 106 tok/s |
| falcon 3 1B | Fast | 106 tok/s |
| Qwen2.5 3B | Fast | 101 tok/s |