Qwen2.5 7B + 0.5B draft needs roughly 24GB of VRAM at our tested precision. A model that doesn't fit doesn't run slowly, it doesn't run. Here's every card from our bench, sorted by measured speed.
| GPU | Speed | VRAM | Basis |
|---|
These cards' VRAM is below the requirement at tested precision, published as data, not hidden.
| GPU | VRAM |
|---|---|
| NVIDIA T4 | 16GB |
Qwen2.5 7B + 0.5B draft needs roughly 24GB of VRAM at our tested precision. 0 of the GPUs on our bench run it; 1 don't have the VRAM for it.