TEST #2985 RESULTS
03/05/2026 - 11:24 PM
ACCELERATOR
MODEL
29.6
tokens/s
generation
381
ms
time to first token
3313
tokens/s
prompt
636
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 9950X 16-Core Processor
RAM
31.2GB
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
4204
tokens/s
31.1
tokens/s
276
ms
pp4096+tg256
3689
tokens/s
27.5
tokens/s
1.15
sec
pp2048+tg256
4083
tokens/s
29.5
tokens/s
536
ms
pp2048+tg768
4077
tokens/s
29.1
tokens/s
535
ms
pp1024+tg1024
4234
tokens/s
30.2
tokens/s
274
ms
pp1280+tg3072
3948
tokens/s
28.7
tokens/s
358
ms
pp384+tg1152
4084
tokens/s
30.5
tokens/s
130
ms
pp64+tg1024
1199
tokens/s
30.5
tokens/s
84
ms
pp16+tg1536
300
tokens/s
29.8
tokens/s
90
ms