TEST #329 RESULTS
04/06/2025 - 12:40 AM
ACCELERATOR
MODEL
52.8
tokens/s
generation
713
ms
time to first token
2124
tokens/s
prompt
540
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 3B Instruct - Q6_K
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
2698
tokens/s
66.9
tokens/s
395
ms
pp4096+tg256
1454
tokens/s
10.3
tokens/s
2.91
sec
pp2048+tg256
2135
tokens/s
48.4
tokens/s
980
ms
pp2048+tg768
2140
tokens/s
45.7
tokens/s
977
ms
pp1024+tg1024
2614
tokens/s
56.4
tokens/s
407
ms
pp1280+tg3072
2485
tokens/s
32.6
tokens/s
532
ms
pp384+tg1152
3041
tokens/s
66.4
tokens/s
139
ms
pp64+tg1024
1644
tokens/s
76.7
tokens/s
50
ms
pp16+tg1536
907
tokens/s
72.1
tokens/s
28
ms