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 5090 · 32GB · Ollama
Other
14 days ago
351.2 tok/s
Decode
1,172.76 tok/s
Prefill
1.63 s
TTFT
30.4 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
AMD Ryzen AI Max+ 395 · 128GB · llama.cpp
Other
14 days ago
46.26 tok/s
Decode
241.55 tok/s
Prefill
2.49 s
TTFT
33.55 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
AMD Ryzen AI Max+ 395 · 128GB · Ollama
Other
14 days ago
44.23 tok/s
Decode
204.06 tok/s
Prefill
0.43 s
TTFT
33.55 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
Apple M5 Max · 128GB · llama.cpp
Other
14 days ago
103.96 tok/s
Decode
353.6 tok/s
Prefill
1.49 s
TTFT
31.13 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
Apple M5 Max · 128GB · llama.cpp
Other
14 days ago
86.99 tok/s
Decode
341.88 tok/s
Prefill
1.42 s
TTFT
46.85 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
Apple M5 Max · 128GB · Ollama
Other
14 days ago
109.91 tok/s
Decode
383.57 tok/s
Prefill
2.4 s
TTFT
27.5 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
Apple M5 Max · 128GB · Ollama
Other
14 days ago
61.49 tok/s
Decode
244.43 tok/s
Prefill
0.72 s
TTFT
56.53 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
Apple M5 Ultra · 512GB · llama.cpp
Other
14 days ago
76.11 tok/s
Decode
389.07 tok/s
Prefill
1.36 s
TTFT
71.65 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
Apple M5 Ultra · 512GB · Ollama
Other
14 days ago
118.22 tok/s
Decode
450.95 tok/s
Prefill
1.07 s
TTFT
49.28 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA H100 80GB HBM3 · 80GB · llama.cpp
Other
14 days ago
343.53 tok/s
Decode
1,745.18 tok/s
Prefill
0.71 s
TTFT
62.58 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA H100 80GB HBM3 · 80GB · Ollama
Other
14 days ago
313.56 tok/s
Decode
1,182.08 tok/s
Prefill
0.81 s
TTFT
41.41 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA H20 · 97GB · Ollama
Other
14 days ago
54.63 tok/s
Decode
291.87 tok/s
Prefill
2.29 s
TTFT
46.85 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA H20 · 97GB · Ollama
Other
14 days ago
58.6 tok/s
Decode
222.5 tok/s
Prefill
0.94 s
TTFT
43.23 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA H20 · 97GB · Strata
Other
14 days ago
68.61 tok/s
Decode
223.86 tok/s
Prefill
2.05 s
TTFT
58.35 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX PRO 6000 Blackwell 96GB · 96GB · vLLM
Other
14 days ago
304.11 tok/s
Decode
1,069.77 tok/s
Prefill
2.36 s
TTFT
42.02 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX PRO 6000 Blackwell 96GB · 96GB · vLLM
Other
14 days ago
310.08 tok/s
Decode
1,540.64 tok/s
Prefill
2.13 s
TTFT
46.85 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX PRO 6000 Blackwell 96GB · 96GB · Ollama
Other
14 days ago
227.94 tok/s
Decode
779.84 tok/s
Prefill
1.38 s
TTFT
51.69 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
Apple M2 Ultra · llama.cpp
Other
14 days ago
155.94 tok/s
Decode
578.17 tok/s
Prefill
2.11 s
TTFT
33.55 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
Apple M2 Ultra · llama.cpp
Other
14 days ago
130 tok/s
Decode
684.42 tok/s
Prefill
1.54 s
TTFT
42.02 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
Apple M2 Ultra · Ollama
Other
14 days ago
110.45 tok/s
Decode
501.39 tok/s
Prefill
0.35 s
TTFT
51.69 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
23 results