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 · llama.cpp
Other
12 days ago
160.59 tok/s
Decode
829.66 tok/s
Prefill
2.32 s
TTFT
15.88 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX 4090 · 24GB · Strata
Other
12 days ago
225.92 tok/s
Decode
741.96 tok/s
Prefill
1.96 s
TTFT
15.88 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX 3090 · 24GB · llama.cpp
Other
12 days ago
94.58 tok/s
Decode
353.95 tok/s
Prefill
1 s
TTFT
15.88 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX 3090 · 24GB · Strata
Other
12 days ago
125.83 tok/s
Decode
630.14 tok/s
Prefill
2.19 s
TTFT
15.88 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
AMD Radeon RX 7900 XTX · 24GB · llama.cpp
Other
12 days ago
102.56 tok/s
Decode
353.32 tok/s
Prefill
2.42 s
TTFT
15.88 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
AMD Radeon RX 7900 XTX · 24GB · Ollama
Other
12 days ago
86.87 tok/s
Decode
421.48 tok/s
Prefill
1.94 s
TTFT
15.88 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX 5090 · 32GB · vLLM
Other
12 days ago
171.53 tok/s
Decode
804.96 tok/s
Prefill
0.25 s
TTFT
30.4 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX 5090 · 32GB · Ollama
Other
12 days ago
279.75 tok/s
Decode
1,289.8 tok/s
Prefill
1.24 s
TTFT
15.88 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX 5080 · 16GB · Ollama
Other
12 days ago
181.19 tok/s
Decode
808.04 tok/s
Prefill
1.57 s
TTFT
15.2 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX 4080 Super · 16GB · llama.cpp
Other
12 days ago
162.68 tok/s
Decode
521.64 tok/s
Prefill
1.22 s
TTFT
15.2 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
AMD Ryzen AI Max+ 395 · 128GB · llama.cpp
Other
12 days ago
35.76 tok/s
Decode
167.23 tok/s
Prefill
0.59 s
TTFT
15.88 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
AMD Ryzen AI Max+ 395 · 128GB · Ollama
Other
12 days ago
33.77 tok/s
Decode
108.98 tok/s
Prefill
1.79 s
TTFT
15.88 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
Apple M5 Max · 128GB · llama.cpp
Other
12 days ago
76.62 tok/s
Decode
265.83 tok/s
Prefill
1.74 s
TTFT
15.88 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
Apple M5 Max · 128GB · Ollama
Other
12 days ago
69.91 tok/s
Decode
321.78 tok/s
Prefill
1.46 s
TTFT
15.88 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
Apple M5 Ultra · 512GB · llama.cpp
Other
12 days ago
130.96 tok/s
Decode
547.83 tok/s
Prefill
1.48 s
TTFT
15.88 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
Apple M5 Ultra · 512GB · Ollama
Other
12 days ago
106.35 tok/s
Decode
353.45 tok/s
Prefill
0.54 s
TTFT
15.88 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA H100 80GB HBM3 · 80GB · Ollama
Other
12 days ago
345.26 tok/s
Decode
1,726.58 tok/s
Prefill
1.8 s
TTFT
15.88 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA H100 80GB HBM3 · 80GB · Strata
Other
12 days ago
317.23 tok/s
Decode
1,729.64 tok/s
Prefill
1.22 s
TTFT
15.88 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA H20 · 97GB · llama.cpp
Other
12 days ago
61.75 tok/s
Decode
319.38 tok/s
Prefill
1.57 s
TTFT
15.88 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA H20 · 97GB · Strata
Other
12 days ago
91.09 tok/s
Decode
326.32 tok/s
Prefill
0.1 s
TTFT
15.88 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
26 results