TEST #336 RESULTS
04/06/2025 - 1:22 AM
ACCELERATOR
MODEL
36.7
tokens/s
generation
1.37
sec
time to first token
1050
tokens/s
prompt
304
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_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
1181
tokens/s
44.1
tokens/s
888
ms
pp4096+tg256
800
tokens/s
6.7
tokens/s
5.27
sec
pp2048+tg256
1087
tokens/s
34.5
tokens/s
1.91
sec
pp2048+tg768
1089
tokens/s
32.7
tokens/s
1.91
sec
pp1024+tg1024
1278
tokens/s
40.0
tokens/s
823
ms
pp1280+tg3072
1230
tokens/s
22.9
tokens/s
1.06
sec
pp384+tg1152
1416
tokens/s
46.7
tokens/s
289
ms
pp64+tg1024
804
tokens/s
53.0
tokens/s
96
ms
pp16+tg1536
561
tokens/s
49.8
tokens/s
45
ms