TEST #560 RESULTS
04/08/2025 - 6:28 AM
ACCELERATOR
MODEL
47.3
tokens/s
generation
550
ms
time to first token
2382
tokens/s
prompt
589
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 5900X 12-Core Processor (znver3)
RAM
127.9GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2935
tokens/s
47.6
tokens/s
370
ms
pp4096+tg256
2262
tokens/s
45.1
tokens/s
1.83
sec
pp2048+tg256
2661
tokens/s
47.4
tokens/s
791
ms
pp2048+tg768
2658
tokens/s
46.8
tokens/s
792
ms
pp1024+tg1024
2705
tokens/s
47.0
tokens/s
401
ms
pp1280+tg3072
2711
tokens/s
46.4
tokens/s
494
ms
pp384+tg1152
3163
tokens/s
48.0
tokens/s
160
ms
pp64+tg1024
1825
tokens/s
48.6
tokens/s
56
ms
pp16+tg1536
515
tokens/s
48.5
tokens/s
52
ms