TEST #1651 RESULTS
10/14/2025 - 12:49 PM
ACCELERATOR
MODEL
5.2
tokens/s
generation
3.38
sec
time to first token
424
tokens/s
prompt
87
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 9900X 12-Core Processor
RAM
61.6GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
486
tokens/s
5.7
tokens/s
2.28
sec
pp4096+tg256
372
tokens/s
1.2
tokens/s
11.85
sec
pp2048+tg256
441
tokens/s
3.8
tokens/s
4.93
sec
pp2048+tg768
440
tokens/s
3.5
tokens/s
4.95
sec
pp1024+tg1024
486
tokens/s
5.1
tokens/s
2.28
sec
pp1280+tg3072
467
tokens/s
2.7
tokens/s
2.94
sec
pp384+tg1152
536
tokens/s
7.1
tokens/s
817
ms
pp64+tg1024
406
tokens/s
9.5
tokens/s
223
ms
pp16+tg1536
178
tokens/s
8.0
tokens/s
147
ms