How we got this number
Each generated token reads the whole model from memory once: 6 GB. The Minisforum UM790 Pro (Ryzen 9 7940HS, 32GB) moves 89.6 GB/s, so the ceiling is 15 tokens/sec. Real machines reach a fraction of that ceiling; we use 60%, 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 7B
Other models on the Minisforum UM790 Pro (Ryzen 9 7940HS, 32GB)
| lfm 2.5 8B (A1B) | Fast | 44 tok/s |
| Llama 3.2 1B | Fast | 41 tok/s |
| Qwen 3 1.7B | Fast | 38 tok/s |
| Granite 3.1 moe 1B | Fast | 38 tok/s |
| minicpm v4.6 1B | Fast | 34 tok/s |
| Gemma 2 2B | Fast | 34 tok/s |