TEST #691 RESULTS
04/11/2025 - 7:52 PM
ACCELERATOR
MODEL
186
tokens/s
generation
102
ms
time to first token
13196
tokens/s
prompt
2888
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 5700X3D 8-Core Processor (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
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
17207
tokens/s
164
tokens/s
65
ms
pp4096+tg256
11910
tokens/s
183
tokens/s
349
ms
pp2048+tg256
15203
tokens/s
193
tokens/s
140
ms
pp2048+tg768
15161
tokens/s
189
tokens/s
140
ms
pp1024+tg1024
17705
tokens/s
192
tokens/s
63
ms
pp1280+tg3072
16622
tokens/s
188
tokens/s
82
ms
pp384+tg1152
18286
tokens/s
188
tokens/s
28
ms
pp64+tg1024
6112
tokens/s
189
tokens/s
16
ms
pp16+tg1536
556
tokens/s
190
tokens/s
35
ms