TEST #1350 RESULTS
08/09/2025 - 10:34 PM
ACCELERATOR
MODEL
30.9
tokens/s
generation
1.95
sec
time to first token
737
tokens/s
prompt
227
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
31.3GB
OS
Linux
Kernel Release
6.8.0-71-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #71-Ubuntu SMP PREEMPT_DYNAMIC Tue Jul 22 16:52:38 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
892
tokens/s
39.6
tokens/s
1.17
sec
pp4096+tg256
559
tokens/s
5.0
tokens/s
7.52
sec
pp2048+tg256
757
tokens/s
28.6
tokens/s
2.74
sec
pp2048+tg768
756
tokens/s
27.1
tokens/s
2.74
sec
pp1024+tg1024
872
tokens/s
33.0
tokens/s
1.20
sec
pp1280+tg3072
846
tokens/s
18.1
tokens/s
1.54
sec
pp384+tg1152
973
tokens/s
39.3
tokens/s
416
ms
pp64+tg1024
605
tokens/s
44.8
tokens/s
125
ms
pp16+tg1536
375
tokens/s
42.5
tokens/s
61
ms