TEST #330 RESULTS
04/06/2025 - 12:43 AM
ACCELERATOR
MODEL
53.6
tokens/s
generation
665
ms
time to first token
2339
tokens/s
prompt
573
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 3B Instruct - Q5_K - Medium
SYSTEM
CPU
AMD Ryzen 9 5950X 16-Core Processor (znver3)
RAM
125.7GB
OS
Linux
Kernel Release
6.13.9-200.fc41.x86_64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Sat Mar 29 01:29:31 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
2986
tokens/s
67.6
tokens/s
358
ms
pp4096+tg256
1534
tokens/s
10.3
tokens/s
2.77
sec
pp2048+tg256
2315
tokens/s
49.1
tokens/s
905
ms
pp2048+tg768
2312
tokens/s
46.0
tokens/s
906
ms
pp1024+tg1024
2882
tokens/s
57.2
tokens/s
370
ms
pp1280+tg3072
2747
tokens/s
32.8
tokens/s
483
ms
pp384+tg1152
3441
tokens/s
67.8
tokens/s
124
ms
pp64+tg1024
1920
tokens/s
78.3
tokens/s
44
ms
pp16+tg1536
916
tokens/s
73.2
tokens/s
28
ms