TEST #1874 RESULTS
11/26/2025 - 7:40 PM
ACCELERATOR
MODEL
125
tokens/s
generation
170
ms
time to first token
7871
tokens/s
prompt
1797
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
125.7GB
OS
Linux
Kernel Release
6.17.7-200.fc42.x86_64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Sun Nov 2 17:43:34 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
10097
tokens/s
126
tokens/s
109
ms
pp4096+tg256
6911
tokens/s
115
tokens/s
601
ms
pp2048+tg256
8710
tokens/s
122
tokens/s
243
ms
pp2048+tg768
8705
tokens/s
121
tokens/s
243
ms
pp1024+tg1024
10088
tokens/s
125
tokens/s
109
ms
pp1280+tg3072
9749
tokens/s
121
tokens/s
140
ms
pp384+tg1152
9871
tokens/s
131
tokens/s
46
ms
pp64+tg1024
5160
tokens/s
134
tokens/s
20
ms
pp16+tg1536
1552
tokens/s
132
tokens/s
18
ms