TEST #1094 RESULTS
06/23/2025 - 9:47 AM
ACCELERATOR
MODEL
50.7
tokens/s
generation
578
ms
time to first token
2189
tokens/s
prompt
577
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
53.6GB
OS
Linux
Kernel Release
5.15.167.4-microsoft-standard-WSL2
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP Tue Nov 5 00:21:55 UTC 2024
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2671
tokens/s
52.2
tokens/s
404
ms
pp4096+tg256
2205
tokens/s
49.2
tokens/s
1.88
sec
pp2048+tg256
2482
tokens/s
52.2
tokens/s
845
ms
pp2048+tg768
2475
tokens/s
51.3
tokens/s
847
ms
pp1024+tg1024
2632
tokens/s
51.3
tokens/s
409
ms
pp1280+tg3072
2530
tokens/s
50.3
tokens/s
526
ms
pp384+tg1152
2695
tokens/s
50.4
tokens/s
173
ms
pp64+tg1024
1594
tokens/s
50.0
tokens/s
59
ms
pp16+tg1536
421
tokens/s
49.6
tokens/s
57
ms