TEST #1000 RESULTS
06/04/2025 - 8:23 PM
ACCELERATOR
MODEL
27.9
tokens/s
generation
2.57
sec
time to first token
502
tokens/s
prompt
176
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 5700X 8-Core Processor (znver3)
RAM
31.3GB
OS
Linux
Kernel Release
6.14.9-300.fc42.x86_64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Thu May 29 14:27:53 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
601
tokens/s
34.3
tokens/s
1.73
sec
pp4096+tg256
471
tokens/s
7.2
tokens/s
8.84
sec
pp2048+tg256
552
tokens/s
26.0
tokens/s
3.75
sec
pp2048+tg768
552
tokens/s
24.3
tokens/s
3.75
sec
pp1024+tg1024
599
tokens/s
30.0
tokens/s
1.74
sec
pp1280+tg3072
575
tokens/s
19.3
tokens/s
2.26
sec
pp384+tg1152
600
tokens/s
34.6
tokens/s
665
ms
pp64+tg1024
217
tokens/s
39.2
tokens/s
317
ms
pp16+tg1536
352
tokens/s
36.7
tokens/s
67
ms