TEST #678 RESULTS
04/10/2025 - 7:11 PM
ACCELERATOR
MODEL
68.0
tokens/s
generation
523
ms
time to first token
2355
tokens/s
prompt
674
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5.1 Coder 7B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 5 5600X 6-Core Processor (znver3)
RAM
95.9GB
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
2846
tokens/s
73.2
tokens/s
374
ms
pp4096+tg256
2472
tokens/s
55.4
tokens/s
1.67
sec
pp2048+tg256
2721
tokens/s
68.7
tokens/s
767
ms
pp2048+tg768
2706
tokens/s
67.7
tokens/s
771
ms
pp1024+tg1024
2828
tokens/s
71.6
tokens/s
377
ms
pp1280+tg3072
2735
tokens/s
64.5
tokens/s
482
ms
pp384+tg1152
2435
tokens/s
72.9
tokens/s
172
ms
pp64+tg1024
1892
tokens/s
69.5
tokens/s
48
ms
pp16+tg1536
564
tokens/s
68.7
tokens/s
43
ms