TEST #624 RESULTS
04/08/2025 - 10:38 PM
ACCELERATOR
MODEL
21.5
tokens/s
generation
2.34
sec
time to first token
604
tokens/s
prompt
177
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
31.2GB
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
662
tokens/s
27.8
tokens/s
1.58
sec
pp4096+tg256
504
tokens/s
8.7
tokens/s
8.24
sec
pp2048+tg256
603
tokens/s
16.2
tokens/s
3.46
sec
pp2048+tg768
604
tokens/s
14.7
tokens/s
3.45
sec
pp1024+tg1024
664
tokens/s
22.1
tokens/s
1.58
sec
pp1280+tg3072
654
tokens/s
12.8
tokens/s
2.00
sec
pp384+tg1152
731
tokens/s
28.5
tokens/s
554
ms
pp64+tg1024
670
tokens/s
32.5
tokens/s
122
ms
pp16+tg1536
348
tokens/s
30.1
tokens/s
72
ms