TEST #1687 RESULTS
10/19/2025 - 4:48 AM
ACCELERATOR
MODEL
6.1
tokens/s
generation
1.51
sec
time to first token
1031
tokens/s
prompt
161
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 7700 8-Core Processor (znver4)
RAM
63.1GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1302
tokens/s
6.6
tokens/s
938
ms
pp4096+tg256
795
tokens/s
2.0
tokens/s
5.65
sec
pp2048+tg256
1103
tokens/s
4.4
tokens/s
2.11
sec
pp2048+tg768
1103
tokens/s
4.0
tokens/s
2.12
sec
pp1024+tg1024
1304
tokens/s
5.8
tokens/s
938
ms
pp1280+tg3072
1193
tokens/s
3.4
tokens/s
1.25
sec
pp384+tg1152
1415
tokens/s
8.2
tokens/s
357
ms
pp64+tg1024
777
tokens/s
11.4
tokens/s
133
ms
pp16+tg1536
286
tokens/s
9.4
tokens/s
99
ms