TEST #1337 RESULTS
08/07/2025 - 8:47 PM
ACCELERATOR
MODEL
45.3
tokens/s
generation
128
ms
time to first token
10888
tokens/s
prompt
1567
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 9950X3D 16-Core Processor
RAM
63.6GB
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
14207
tokens/s
46.1
tokens/s
94
ms
pp4096+tg256
12204
tokens/s
44.7
tokens/s
358
ms
pp2048+tg256
13851
tokens/s
44.6
tokens/s
171
ms
pp2048+tg768
14693
tokens/s
44.9
tokens/s
161
ms
pp1024+tg1024
15659
tokens/s
45.0
tokens/s
85
ms
pp1280+tg3072
13444
tokens/s
44.8
tokens/s
117
ms
pp384+tg1152
11527
tokens/s
45.4
tokens/s
64
ms
pp64+tg1024
1918
tokens/s
46.3
tokens/s
52
ms
pp16+tg1536
490
tokens/s
45.8
tokens/s
51
ms