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
71.3 tok/s
Decode
534.8 tok/s
Prefill
0.19 s
TTFT
5.4 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX 5070 · 12GB · Strata
Other
Today
156.3 tok/s
Decode
1,172.3 tok/s
Prefill
0.09 s
TTFT
4.8 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX 3060 12GB · 12GB · llama.cpp
Other
Today
57.3 tok/s
Decode
429.8 tok/s
Prefill
0.23 s
TTFT
5.4 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
3 results