TEST #1457 RESULTS
08/30/2025 - 9:44 AM
ACCELERATOR
MODEL
157
tokens/s
generation
183
ms
time to first token
7533
tokens/s
prompt
1865
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 5900HX with Radeon Graphics (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
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
9689
tokens/s
158
tokens/s
113
ms
pp4096+tg256
6319
tokens/s
151
tokens/s
656
ms
pp2048+tg256
8241
tokens/s
155
tokens/s
255
ms
pp2048+tg768
8099
tokens/s
160
tokens/s
259
ms
pp1024+tg1024
9359
tokens/s
162
tokens/s
116
ms
pp1280+tg3072
8741
tokens/s
157
tokens/s
153
ms
pp384+tg1152
12032
tokens/s
162
tokens/s
38
ms
pp64+tg1024
4752
tokens/s
157
tokens/s
20
ms
pp16+tg1536
567
tokens/s
153
tokens/s
34
ms