TEST #1020 RESULTS
06/08/2025 - 11:38 PM
ACCELERATOR
MODEL
7.8
tokens/s
generation
26.60
sec
time to first token
53
tokens/s
prompt
25
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 5700X3D 8-Core Processor (znver3)
RAM
47.9GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
46
tokens/s
8.1
tokens/s
22.23
sec
pp4096+tg256
47
tokens/s
6.7
tokens/s
87.43
sec
pp2048+tg256
52
tokens/s
7.6
tokens/s
39.44
sec
pp2048+tg768
49
tokens/s
7.7
tokens/s
41.91
sec
pp1024+tg1024
58
tokens/s
7.9
tokens/s
17.89
sec
pp1280+tg3072
58
tokens/s
7.5
tokens/s
22.35
sec
pp384+tg1152
60
tokens/s
8.1
tokens/s
6.47
sec
pp64+tg1024
55
tokens/s
8.2
tokens/s
1.28
sec
pp16+tg1536
51
tokens/s
8.1
tokens/s
437
ms