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 · llama.cpp
Other
3 days ago
319.07 tok/s
Decode
1,265.71 tok/s
Prefill
0.22 s
TTFT
2.88 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX 5090 · 32GB · llama.cpp
Other
3 days ago
358.97 tok/s
Decode
1,824.25 tok/s
Prefill
1.68 s
TTFT
3.31 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA RTX 5090 · 32GB · vLLM
Other
3 days ago
285.37 tok/s
Decode
1,069.59 tok/s
Prefill
1.76 s
TTFT
2.75 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
AMD Ryzen AI Max+ 395 · 128GB · llama.cpp
Other
3 days ago
339.19 tok/s
Decode
1,541.81 tok/s
Prefill
0.96 s
TTFT
2.81 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
AMD Ryzen AI Max+ 395 · 128GB · llama.cpp
Other
3 days ago
367.02 tok/s
Decode
1,342.6 tok/s
Prefill
1.93 s
TTFT
2.78 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
AMD Ryzen AI Max+ 395 · 128GB · Strata
Other
3 days ago
347.23 tok/s
Decode
1,400.32 tok/s
Prefill
0.76 s
TTFT
2.65 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
Apple M5 Max · 128GB · vLLM
Other
3 days ago
291.82 tok/s
Decode
1,370.02 tok/s
Prefill
1.18 s
TTFT
2.6 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
Apple M5 Max · 128GB · Strata
Other
3 days ago
343.91 tok/s
Decode
1,513.7 tok/s
Prefill
2.2 s
TTFT
2.54 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
Apple M5 Max · 128GB · Strata
Other
3 days ago
305.21 tok/s
Decode
1,469.7 tok/s
Prefill
1.32 s
TTFT
3.04 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA DGX Spark · 128GB · llama.cpp
Other
3 days ago
344.66 tok/s
Decode
1,710.46 tok/s
Prefill
0.34 s
TTFT
2.6 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA DGX Spark · 128GB · Strata
Other
3 days ago
295.77 tok/s
Decode
1,437.09 tok/s
Prefill
1.77 s
TTFT
2.6 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA DGX Spark · 128GB · Strata
Other
3 days ago
294.11 tok/s
Decode
1,222.22 tok/s
Prefill
0.86 s
TTFT
3.08 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA Jetson AGX Orin 64GB · 64GB · llama.cpp
Other
3 days ago
243.52 tok/s
Decode
900.17 tok/s
Prefill
1.32 s
TTFT
2.54 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA Jetson AGX Orin 64GB · 64GB · llama.cpp
Other
3 days ago
199.9 tok/s
Decode
998.9 tok/s
Prefill
0.95 s
TTFT
2.78 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
NVIDIA Jetson AGX Orin 64GB · 64GB · Strata
Other
3 days ago
310.9 tok/s
Decode
1,483.77 tok/s
Prefill
1.17 s
TTFT
2.75 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
AMD Strix Halo (Radeon 8060S) · llama.cpp
Other
3 days ago
124.48 tok/s
Decode
656.36 tok/s
Prefill
0.83 s
TTFT
4.04 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
AMD Strix Halo (Radeon 8060S) · llama.cpp
Other
3 days ago
171.39 tok/s
Decode
894.49 tok/s
Prefill
1.55 s
TTFT
3.15 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
AMD Strix Halo (Radeon 8060S) · vLLM
Other
3 days ago
228.54 tok/s
Decode
950.08 tok/s
Prefill
2.25 s
TTFT
3.04 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
2x AMD Strix Halo · Ollama
Other
3 days ago
347.47 tok/s
Decode
1,631.19 tok/s
Prefill
2.1 s
TTFT
2.78 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
2x AMD Strix Halo · Ollama
Other
3 days ago
256.99 tok/s
Decode
1,220.11 tok/s
Prefill
0.82 s
TTFT
3.31 GB
VRAM
Sources: Other · 1 runs · 1 independent sources
88 results