TEST #424 RESULTS
04/06/2025 - 9:08 PM
ACCELERATOR
MODEL
6.2
tokens/s
generation
35.56
sec
time to first token
38
tokens/s
prompt
19
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
31.9GB
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
40
tokens/s
6.6
tokens/s
25.65
sec
pp4096+tg256
35
tokens/s
5.4
tokens/s
116.03
sec
pp2048+tg256
38
tokens/s
6.2
tokens/s
53.46
sec
pp2048+tg768
38
tokens/s
6.0
tokens/s
53.73
sec
pp1024+tg1024
40
tokens/s
6.3
tokens/s
25.99
sec
pp1280+tg3072
39
tokens/s
5.9
tokens/s
32.96
sec
pp384+tg1152
41
tokens/s
6.5
tokens/s
9.61
sec
pp64+tg1024
35
tokens/s
6.6
tokens/s
1.96
sec
pp16+tg1536
32
tokens/s
6.5
tokens/s
660
ms