TEST #670 RESULTS
04/10/2025 - 3:05 PM
ACCELERATOR
MODEL
37.3
tokens/s
generation
1.07
sec
time to first token
1170
tokens/s
prompt
344
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B 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
1415
tokens/s
40.7
tokens/s
748
ms
pp4096+tg256
1181
tokens/s
29.3
tokens/s
3.50
sec
pp2048+tg256
1321
tokens/s
36.8
tokens/s
1.58
sec
pp2048+tg768
1316
tokens/s
36.3
tokens/s
1.58
sec
pp1024+tg1024
1387
tokens/s
38.2
tokens/s
763
ms
pp1280+tg3072
1338
tokens/s
34.7
tokens/s
981
ms
pp384+tg1152
1227
tokens/s
39.6
tokens/s
338
ms
pp64+tg1024
999
tokens/s
40.3
tokens/s
88
ms
pp16+tg1536
347
tokens/s
40.0
tokens/s
70
ms