TEST #4241 RESULTS
10/03/2026 - 2:42 PM
ACCELERATOR
MODEL
6.2
tokens/s
generation
27.83
sec
time to first token
50
tokens/s
prompt
22
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 3900X 12-Core Processor (znver2)
RAM
31.9GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
55
tokens/s
6.3
tokens/s
18.93
sec
pp4096+tg256
45
tokens/s
5.5
tokens/s
91.28
sec
pp2048+tg256
49
tokens/s
5.9
tokens/s
41.56
sec
pp2048+tg768
48
tokens/s
5.8
tokens/s
42.84
sec
pp1024+tg1024
48
tokens/s
6.1
tokens/s
21.61
sec
pp1280+tg3072
50
tokens/s
5.9
tokens/s
25.64
sec
pp384+tg1152
58
tokens/s
6.6
tokens/s
6.79
sec
pp64+tg1024
57
tokens/s
6.8
tokens/s
1.26
sec
pp16+tg1536
42
tokens/s
6.7
tokens/s
531
ms