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 Spark · 128GB · llama.cpp
Other
16 days ago
8.81 tok/s
Decode
37.51 tok/s
Prefill
2.19 s
TTFT
54.83 GB
VRAM
Sources: Other · 2 runs · 1 independent sources
NVIDIA RTX Spark · 128GB · llama.cpp
Other
16 days ago
6.42 tok/s
Decode
24.36 tok/s
Prefill
0.53 s
TTFT
67.3 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX Spark · 128GB · Ollama
Other
16 days ago
7.6 tok/s
Decode
28.29 tok/s
Prefill
2.88 s
TTFT
54.83 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX Spark · 128GB · Ollama
Other
16 days ago
7.47 tok/s
Decode
38.07 tok/s
Prefill
1.92 s
TTFT
58.8 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX Spark · 128GB · Ollama
Other
16 days ago
6.14 tok/s
Decode
31.39 tok/s
Prefill
1.35 s
TTFT
67.3 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
AMD Radeon RX 7900 XTX · 24GB · vLLM
Other
17 days ago
68.56 tok/s
Decode
341.84 tok/s
Prefill
1.19 s
TTFT
22.8 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX 5090 · 32GB · llama.cpp
Other
17 days ago
200.6 tok/s
Decode
837.93 tok/s
Prefill
2.39 s
TTFT
30.4 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
AMD Ryzen AI Max+ 395 · 128GB · vLLM
Other
17 days ago
9.75 tok/s
Decode
49.87 tok/s
Prefill
2.04 s
TTFT
107 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
AMD Ryzen AI Max+ 395 · 128GB · vLLM
Other
17 days ago
13.23 tok/s
Decode
57.54 tok/s
Prefill
2.09 s
TTFT
67.3 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
AMD Ryzen AI Max+ 395 · 128GB · Ollama
Other
17 days ago
19.34 tok/s
Decode
100.78 tok/s
Prefill
0.82 s
TTFT
42.92 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
Apple M5 Max · 128GB · llama.cpp
Other
17 days ago
42.74 tok/s
Decode
158.84 tok/s
Prefill
1.45 s
TTFT
42.92 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
Apple M5 Max · 128GB · llama.cpp
Other
17 days ago
30.73 tok/s
Decode
132.88 tok/s
Prefill
0.81 s
TTFT
58.8 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
Apple M5 Max · 128GB · Ollama
Other
17 days ago
46.88 tok/s
Decode
178.13 tok/s
Prefill
0.6 s
TTFT
37.25 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
Apple M5 Ultra · 512GB · llama.cpp
Other
17 days ago
89.58 tok/s
Decode
565.47 tok/s
Prefill
0.33 s
TTFT
19.46 GB
VRAM
Sources: Other · 2 runs · 1 independent sources
Apple M5 Ultra · 512GB · Ollama
Other
17 days ago
74.38 tok/s
Decode
283.32 tok/s
Prefill
1.58 s
TTFT
33.29 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
Apple M5 Ultra · 512GB · Ollama
Other
17 days ago
60.73 tok/s
Decode
250.32 tok/s
Prefill
0.69 s
TTFT
38.96 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA H100 80GB HBM3 · 80GB · vLLM
Other
17 days ago
224.13 tok/s
Decode
1,208.86 tok/s
Prefill
0.75 s
TTFT
48.59 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA H100 80GB HBM3 · 80GB · vLLM
Other
17 days ago
206.52 tok/s
Decode
1,029.93 tok/s
Prefill
0.84 s
TTFT
54.83 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA H100 80GB HBM3 · 80GB · Strata
Other
17 days ago
325.92 tok/s
Decode
1,772.8 tok/s
Prefill
0.35 s
TTFT
31.58 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA H20 · 97GB · llama.cpp
Other
17 days ago
42.1 tok/s
Decode
229.32 tok/s
Prefill
2.23 s
TTFT
29.32 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
119 results