TEST #1847 RESULTS
11/22/2025 - 9:20 AM
ACCELERATOR
MODEL
44.1
tokens/s
generation
154
ms
time to first token
8711
tokens/s
prompt
1355
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 7800X3D 8-Core Processor (znver4)
RAM
31.6GB
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
11393
tokens/s
45.3
tokens/s
114
ms
pp4096+tg256
9953
tokens/s
40.8
tokens/s
437
ms
pp2048+tg256
11166
tokens/s
46.8
tokens/s
204
ms
pp2048+tg768
10995
tokens/s
41.7
tokens/s
208
ms
pp1024+tg1024
12002
tokens/s
46.3
tokens/s
107
ms
pp1280+tg3072
10354
tokens/s
40.2
tokens/s
144
ms
pp384+tg1152
10274
tokens/s
46.2
tokens/s
61
ms
pp64+tg1024
1787
tokens/s
44.8
tokens/s
57
ms
pp16+tg1536
471
tokens/s
44.4
tokens/s
55
ms