TEST #302 RESULTS
04/05/2025 - 9:09 PM
ACCELERATOR
MODEL
3.3
tokens/s
generation
17.73
sec
time to first token
73
tokens/s
prompt
24
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - BF16
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
80
tokens/s
3.3
tokens/s
13.08
sec
pp4096+tg256
73
tokens/s
3.2
tokens/s
56.78
sec
pp2048+tg256
77
tokens/s
3.3
tokens/s
26.74
sec
pp2048+tg768
77
tokens/s
3.3
tokens/s
26.90
sec
pp1024+tg1024
80
tokens/s
3.3
tokens/s
13.08
sec
pp1280+tg3072
80
tokens/s
3.3
tokens/s
16.28
sec
pp384+tg1152
87
tokens/s
3.3
tokens/s
4.73
sec
pp64+tg1024
72
tokens/s
3.4
tokens/s
1.18
sec
pp16+tg1536
32
tokens/s
3.3
tokens/s
801
ms