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 5080 SUPER · 24GB · vLLM
Other
Today
90.7 tok/s
Decode
680.3 tok/s
Prefill
0.15 s
TTFT
11 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX 5080 SUPER · 24GB · vLLM
Other
Today
41.4 tok/s
Decode
310.5 tok/s
Prefill
0.32 s
TTFT
23.5 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX 5080 SUPER · 24GB · vLLM
Other
Today
50.6 tok/s
Decode
379.5 tok/s
Prefill
0.26 s
TTFT
19.3 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX 5080 SUPER · 24GB · llama.cpp
Other
Today
83.2 tok/s
Decode
624 tok/s
Prefill
0.16 s
TTFT
11 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX 5080 SUPER · 24GB · llama.cpp
Other
Today
38 tok/s
Decode
285 tok/s
Prefill
0.35 s
TTFT
23.5 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX 5080 SUPER · 24GB · llama.cpp
Other
Today
46.5 tok/s
Decode
348.8 tok/s
Prefill
0.29 s
TTFT
19.3 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX 5070 SUPER · 18GB · vLLM
Other
Today
72.5 tok/s
Decode
543.8 tok/s
Prefill
0.18 s
TTFT
11 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX 5070 SUPER · 18GB · vLLM
Other
Today
33.1 tok/s
Decode
248.3 tok/s
Prefill
0.4 s
TTFT
18 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX 5070 SUPER · 18GB · vLLM
Other
Today
40.5 tok/s
Decode
303.8 tok/s
Prefill
0.33 s
TTFT
18 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX 5070 SUPER · 18GB · llama.cpp
Other
Today
66.6 tok/s
Decode
499.5 tok/s
Prefill
0.2 s
TTFT
11 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX 5070 SUPER · 18GB · llama.cpp
Other
Today
30.4 tok/s
Decode
228 tok/s
Prefill
0.44 s
TTFT
18 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX 5070 SUPER · 18GB · llama.cpp
Other
Today
37.2 tok/s
Decode
279 tok/s
Prefill
0.36 s
TTFT
18 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX 4080 Super · 16GB · vLLM
Other
Today
59.6 tok/s
Decode
447 tok/s
Prefill
0.22 s
TTFT
11 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX 4080 Super · 16GB · vLLM
Other
Today
27.2 tok/s
Decode
204 tok/s
Prefill
0.49 s
TTFT
16 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX 4080 Super · 16GB · vLLM
Other
Today
33.3 tok/s
Decode
249.7 tok/s
Prefill
0.4 s
TTFT
16 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX 4080 Super · 16GB · llama.cpp
Other
Today
54.7 tok/s
Decode
410.3 tok/s
Prefill
0.24 s
TTFT
11 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX 4080 Super · 16GB · llama.cpp
Other
Today
25 tok/s
Decode
187.5 tok/s
Prefill
0.53 s
TTFT
16 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX 4080 Super · 16GB · llama.cpp
Other
Today
30.5 tok/s
Decode
228.8 tok/s
Prefill
0.44 s
TTFT
16 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX 5070 Ti · 16GB · vLLM
Other
Today
72.5 tok/s
Decode
543.8 tok/s
Prefill
0.18 s
TTFT
11 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX 5070 Ti · 16GB · vLLM
Other
Today
33.1 tok/s
Decode
248.3 tok/s
Prefill
0.4 s
TTFT
16 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
36 results