TEST #1090 RESULTS
06/23/2025 - 8:55 AM
ACCELERATOR
MODEL
193
tokens/s
generation
94
ms
time to first token
14107
tokens/s
prompt
3073
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 5900X 12-Core Processor (znver3)
RAM
53.6GB
OS
Linux
Kernel Release
5.15.167.4-microsoft-standard-WSL2
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP Tue Nov 5 00:21:55 UTC 2024
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
17915
tokens/s
188
tokens/s
62
ms
pp4096+tg256
12936
tokens/s
183
tokens/s
322
ms
pp2048+tg256
16276
tokens/s
195
tokens/s
131
ms
pp2048+tg768
16393
tokens/s
188
tokens/s
130
ms
pp1024+tg1024
18586
tokens/s
198
tokens/s
60
ms
pp1280+tg3072
17638
tokens/s
193
tokens/s
77
ms
pp384+tg1152
19597
tokens/s
198
tokens/s
25
ms
pp64+tg1024
6621
tokens/s
195
tokens/s
15
ms
pp16+tg1536
999
tokens/s
197
tokens/s
20
ms