TEST #3306 RESULTS
04/14/2026 - 10:32 PM
ACCELERATOR
MODEL
32.4
tokens/s
generation
1.27
sec
time to first token
1016
tokens/s
prompt
296
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 5 5600 6-Core Processor (znver3)
RAM
62.7GB
OS
Linux
Kernel Release
6.17.0-20-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #20~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Thu Mar 19 01:28:37 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1174
tokens/s
34.1
tokens/s
905
ms
pp4096+tg256
979
tokens/s
29.8
tokens/s
4.22
sec
pp2048+tg256
1135
tokens/s
32.9
tokens/s
1.84
sec
pp2048+tg768
1121
tokens/s
32.2
tokens/s
1.86
sec
pp1024+tg1024
1175
tokens/s
32.5
tokens/s
904
ms
pp1280+tg3072
1086
tokens/s
30.3
tokens/s
1.21
sec
pp384+tg1152
1187
tokens/s
33.2
tokens/s
352
ms
pp64+tg1024
940
tokens/s
33.7
tokens/s
108
ms
pp16+tg1536
346
tokens/s
33.3
tokens/s
74
ms