TEST #114 RESULTS
03/28/2025 - 9:51 PM
ACCELERATOR
MODEL
29.9
tokens/s
generation
555
ms
time to first token
2424
tokens/s
prompt
507
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 5 7600 6-Core Processor (znver4)
RAM
30.6GB
OS
Linux
Kernel Release
6.8.0-45-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #45~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Wed Sep 11 15:25:05 UTC 2
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
3169
tokens/s
32.7
tokens/s
354
ms
pp4096+tg256
2162
tokens/s
24.8
tokens/s
1.94
sec
pp2048+tg256
2688
tokens/s
29.0
tokens/s
796
ms
pp2048+tg768
2685
tokens/s
28.1
tokens/s
797
ms
pp1024+tg1024
3178
tokens/s
30.4
tokens/s
354
ms
pp1280+tg3072
3006
tokens/s
27.3
tokens/s
458
ms
pp384+tg1152
3283
tokens/s
32.0
tokens/s
149
ms
pp64+tg1024
1283
tokens/s
32.9
tokens/s
78
ms
pp16+tg1536
364
tokens/s
32.2
tokens/s
74
ms