How we got this number
Each generated token reads the whole model from memory once: 1.9 GB. The NVIDIA DGX Spark (128GB) moves 273 GB/s, so the ceiling is 120+ 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 Qwen2.5 Coder 3B
| Mac mini M5 Pro (24GB) | 120+ tok/s | Check price → |
| Mac mini M5 Pro (64GB) | 120+ tok/s | Check price → |
| Mac Studio M5 Max (40-core GPU, 64GB) | 120+ tok/s | Check price → |
| Mac Studio M5 Ultra (96GB) | 120+ tok/s | Check price → |
Other models on the NVIDIA DGX Spark (128GB)
| DeepSeek-R1 1.5B | Fast | 120+ tok/s |
| Llama 3.2 1B | Fast | 120+ tok/s |
| Qwen 3 1.7B | Fast | 120+ tok/s |
| Qwen3.5 0.8B | Fast | 120+ tok/s |
| Qwen 1.8B | Fast | 120+ tok/s |
| Granite 3.1 moe 1B | Fast | 120+ tok/s |