How we got this number
Each generated token reads the active part of the model from memory once: 2.9 GB. The Beelink SER7 (Ryzen 7 7840HS, 32GB) moves 89.6 GB/s, so the ceiling is 31 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 Gemma 4 26B (A4B)
Other models on the Beelink SER7 (Ryzen 7 7840HS, 32GB)
| lfm 2.5 8B (A1B) | Fast | 44 tok/s |
| Qwen 3 30B (A3B) | Comfortable | 16 tok/s |
| Qwen3 Coder 30B (A3B) | Comfortable | 16 tok/s |
| Qwen 3-VL 30B (A3B) | Comfortable | 15 tok/s |
| Llama 2 7B | Comfortable | 14 tok/s |
| Code Llama 7B | Comfortable | 14 tok/s |