TEST #476 RESULTS
04/07/2025 - 5:34 AM
ACCELERATOR
MODEL
35.5
tokens/s
generation
1.57
sec
time to first token
926
tokens/s
prompt
276
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
62.7GB
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
1110
tokens/s
44.7
tokens/s
945
ms
pp4096+tg256
697
tokens/s
6.1
tokens/s
6.04
sec
pp2048+tg256
931
tokens/s
33.3
tokens/s
2.23
sec
pp2048+tg768
928
tokens/s
31.2
tokens/s
2.24
sec
pp1024+tg1024
1097
tokens/s
38.4
tokens/s
957
ms
pp1280+tg3072
1053
tokens/s
21.4
tokens/s
1.24
sec
pp384+tg1152
1226
tokens/s
44.8
tokens/s
332
ms
pp64+tg1024
786
tokens/s
51.4
tokens/s
98
ms
pp16+tg1536
504
tokens/s
48.3
tokens/s
48
ms