TEST #606 RESULTS
04/08/2025 - 3:12 PM
ACCELERATOR
MODEL
27.3
tokens/s
generation
2.46
sec
time to first token
607
tokens/s
prompt
189
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 5700X 8-Core Processor (znver3)
RAM
31.3GB
OS
Linux
Kernel Release
6.13.8-200.fc41.x86_64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Sun Mar 23 05:03:09 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
696
tokens/s
34.9
tokens/s
1.50
sec
pp4096+tg256
441
tokens/s
4.1
tokens/s
9.53
sec
pp2048+tg256
594
tokens/s
25.5
tokens/s
3.48
sec
pp2048+tg768
594
tokens/s
24.0
tokens/s
3.48
sec
pp1024+tg1024
696
tokens/s
29.5
tokens/s
1.50
sec
pp1280+tg3072
667
tokens/s
15.7
tokens/s
1.95
sec
pp384+tg1152
762
tokens/s
35.0
tokens/s
528
ms
pp64+tg1024
633
tokens/s
39.6
tokens/s
123
ms
pp16+tg1536
380
tokens/s
37.6
tokens/s
63
ms