TEST #298 RESULTS
04/05/2025 - 4:33 PM
ACCELERATOR
MODEL
7.6
tokens/s
generation
11.64
sec
time to first token
120
tokens/s
prompt
43
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q6_K
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
126
tokens/s
7.8
tokens/s
8.28
sec
pp4096+tg256
105
tokens/s
7.2
tokens/s
39.04
sec
pp2048+tg256
118
tokens/s
7.6
tokens/s
17.43
sec
pp2048+tg768
118
tokens/s
7.5
tokens/s
17.46
sec
pp1024+tg1024
127
tokens/s
7.6
tokens/s
8.22
sec
pp1280+tg3072
125
tokens/s
7.4
tokens/s
10.37
sec
pp384+tg1152
133
tokens/s
7.8
tokens/s
3.03
sec
pp64+tg1024
131
tokens/s
7.8
tokens/s
619
ms
pp16+tg1536
96
tokens/s
7.8
tokens/s
294
ms