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 4090 · 24GB · Ollama
Other
14 days ago
130.35 tok/s
Decode
593.51 tok/s
Prefill
0.84 s
TTFT
22.8 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
AMD Ryzen AI Max+ 395 · 128GB · llama.cpp
Other
14 days ago
26.2 tok/s
Decode
94.34 tok/s
Prefill
0.65 s
TTFT
46.33 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
AMD Ryzen AI Max+ 395 · 128GB · vLLM
Other
14 days ago
27.6 tok/s
Decode
131.32 tok/s
Prefill
1.78 s
TTFT
46.33 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
Apple M5 Max · 128GB · llama.cpp
Other
14 days ago
59.77 tok/s
Decode
305.47 tok/s
Prefill
0.51 s
TTFT
44.06 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
Apple M5 Max · 128GB · llama.cpp
Other
14 days ago
63.7 tok/s
Decode
294.17 tok/s
Prefill
1.57 s
TTFT
40.66 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
Apple M5 Max · 128GB · Ollama
Other
14 days ago
25.66 tok/s
Decode
97.32 tok/s
Prefill
0.16 s
TTFT
107 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
Apple M5 Ultra · 512GB · llama.cpp
Other
14 days ago
90.54 tok/s
Decode
497.72 tok/s
Prefill
0.45 s
TTFT
40.66 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
Apple M5 Ultra · 512GB · llama.cpp
Other
14 days ago
71.27 tok/s
Decode
325.67 tok/s
Prefill
0.71 s
TTFT
53.13 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
Apple M5 Ultra · 512GB · Ollama
Other
14 days ago
81.44 tok/s
Decode
327.07 tok/s
Prefill
1.59 s
TTFT
44.06 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA H100 80GB HBM3 · 80GB · llama.cpp
Other
14 days ago
342.54 tok/s
Decode
1,113.53 tok/s
Prefill
2.31 s
TTFT
46.33 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA H100 80GB HBM3 · 80GB · Strata
Other
14 days ago
345.96 tok/s
Decode
1,251.15 tok/s
Prefill
1.63 s
TTFT
38.96 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA H20 · 97GB · llama.cpp
Other
14 days ago
18.55 tok/s
Decode
67.93 tok/s
Prefill
0.56 s
TTFT
92.15 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA H20 · 97GB · vLLM
Other
14 days ago
45.95 tok/s
Decode
201.36 tok/s
Prefill
0.65 s
TTFT
44.06 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX PRO 6000 Blackwell 96GB · 96GB · vLLM
Other
14 days ago
228.17 tok/s
Decode
758.2 tok/s
Prefill
1.08 s
TTFT
37.25 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX PRO 6000 Blackwell 96GB · 96GB · vLLM
Other
14 days ago
145.66 tok/s
Decode
731.49 tok/s
Prefill
1.37 s
TTFT
54.83 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX PRO 6000 Blackwell 96GB · 96GB · Ollama
Other
14 days ago
214.08 tok/s
Decode
806.7 tok/s
Prefill
0.3 s
TTFT
37.25 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX PRO 6000 Blackwell 96GB · 96GB · Ollama
Other
14 days ago
135.94 tok/s
Decode
501.24 tok/s
Prefill
1.93 s
TTFT
53.13 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
Apple M2 Ultra · llama.cpp
Other
14 days ago
102.29 tok/s
Decode
417.96 tok/s
Prefill
1.66 s
TTFT
31.58 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
Apple M2 Ultra · llama.cpp
Other
14 days ago
67.37 tok/s
Decode
314.26 tok/s
Prefill
2.02 s
TTFT
54.83 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
Apple M2 Ultra · Ollama
Other
14 days ago
100.6 tok/s
Decode
448.02 tok/s
Prefill
2.5 s
TTFT
25.91 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
26 results