TEST #333 RESULTS
04/06/2025 - 1:05 AM
ACCELERATOR
MODEL
29.5
tokens/s
generation
1.11
sec
time to first token
1389
tokens/s
prompt
333
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q8_0
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
1572
tokens/s
35.8
tokens/s
679
ms
pp4096+tg256
945
tokens/s
6.5
tokens/s
4.48
sec
pp2048+tg256
1375
tokens/s
28.9
tokens/s
1.52
sec
pp2048+tg768
1376
tokens/s
27.4
tokens/s
1.52
sec
pp1024+tg1024
1699
tokens/s
32.1
tokens/s
631
ms
pp1280+tg3072
1625
tokens/s
20.1
tokens/s
817
ms
pp384+tg1152
2043
tokens/s
36.1
tokens/s
212
ms
pp64+tg1024
1342
tokens/s
40.2
tokens/s
70
ms
pp16+tg1536
524
tokens/s
38.1
tokens/s
53
ms