Each row is a run configuration (model + hardware + framework + quantization); repeated runs of the same setup are merged — raw counts appear in each result’s source line.
NVIDIA RTX 5060 SUPER · 12GB · llama.cpp
Other
Today
388.3 tok/s
Decode
2,912.3 tok/s
Prefill
0.03 s
TTFT
1.4 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX 5070 · 12GB · llama.cpp
Other
Today
582.4 tok/s
Decode
4,368 tok/s
Prefill
0.02 s
TTFT
1.4 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX 3060 12GB · 12GB · llama.cpp
Other
Today
312 tok/s
Decode
2,340 tok/s
Prefill
0.04 s
TTFT
1.4 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
3 results