Rig report
NVIDIA RTX 4080 (16GB)
16.0 GB memory · 717 GB/s · 12 of 18 tracked models fit
Best model it can run
Gemma 4 26B-A4B (MoE)Tight / slow
Q3_K_M · 10.9 GB · 107–161 tok/s · capability 79/100
Fastest that fits: Qwen3 30B-A3B (MoE) at 188–282 tok/s
Have a NVIDIA RTX 4080 (16GB)? Add your real benchmark → to sharpen these numbers for everyone.
Estimates from device specs and model architectures, refined by community benchmarks. See the methodology.