How we got this number
Each generated token reads the active part of the 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 Qwen3 Coder 30B (A3B)
Other models on the NVIDIA DGX Spark (128GB)
| lfm 2.5 8B (A1B) | Fast | 120+ tok/s |
| Qwen 3 30B (A3B) | Fast | 56 tok/s |
| Qwen 3-VL 30B (A3B) | Fast | 53 tok/s |
| Llama 2 7B | Fast | 50 tok/s |
| Code Llama 7B | Fast | 50 tok/s |
| DeepSeek Coder 6.7B | Fast | 50 tok/s |