How we got this number
Each generated token reads the whole model from memory once: 3.2 GB. The NVIDIA DGX Spark (128GB) moves 273 GB/s, so the ceiling is 85 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-VL 3B
Other models on the NVIDIA DGX Spark (128GB)
| lfm 2.5 8B (A1B) | Fast | 120+ tok/s |
| 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 |