TEST #1493 RESULTS
09/08/2025 - 7:44 PM
ACCELERATOR
MODEL
45.0
tokens/s
generation
122
ms
time to first token
11332
tokens/s
prompt
1613
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
15548
tokens/s
46.1
tokens/s
88
ms
pp4096+tg256
14027
tokens/s
43.9
tokens/s
315
ms
pp2048+tg256
14788
tokens/s
44.8
tokens/s
161
ms
pp2048+tg768
14534
tokens/s
44.1
tokens/s
163
ms
pp1024+tg1024
15970
tokens/s
44.8
tokens/s
86
ms
pp1280+tg3072
12887
tokens/s
44.2
tokens/s
122
ms
pp384+tg1152
11814
tokens/s
45.5
tokens/s
55
ms
pp64+tg1024
1909
tokens/s
46.1
tokens/s
53
ms
pp16+tg1536
510
tokens/s
45.6
tokens/s
51
ms