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 PRO 6000 Blackwell · 96GB · vLLM
Other
2026-10-06
31.9 tok/s
Decode
239.3 tok/s
Prefill
0.42 s
TTFT
48.3 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX PRO 6000 Blackwell · 96GB · vLLM
Other
2026-10-06
38.3 tok/s
Decode
287.3 tok/s
Prefill
0.35 s
TTFT
40.3 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
2x NVIDIA RTX 5090 · 64GB · vLLM
Other
2026-10-06
— tok/s
Decode
— tok/s
Prefill
— s
TTFT
48.3 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
2x NVIDIA RTX 5090 · 64GB · vLLM
Other
2026-10-06
— tok/s
Decode
— tok/s
Prefill
— s
TTFT
40.3 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX 5090 · 32GB · vLLM
Other
2026-10-06
31.9 tok/s
Decode
239.3 tok/s
Prefill
0.42 s
TTFT
32 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX 5090 · 32GB · vLLM
Other
2026-10-06
38.3 tok/s
Decode
287.3 tok/s
Prefill
0.35 s
TTFT
32 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX 4090 · 24GB · vLLM
Other
2026-10-06
17.9 tok/s
Decode
134.3 tok/s
Prefill
0.74 s
TTFT
24 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX 4090 · 24GB · vLLM
Other
2026-10-06
21.5 tok/s
Decode
161.3 tok/s
Prefill
0.62 s
TTFT
24 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
8 results