TEST #798 RESULTS
05/03/2025 - 2:21 PM
ACCELERATOR
MODEL
201
tokens/s
generation
236
ms
time to first token
6022
tokens/s
prompt
1725
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 5950X 16-Core Processor (znver3)
RAM
125.7GB
OS
Linux
Kernel Release
6.11.0-112021-tuxedo
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #21~24.04.1tux1 SMP PREEMPT_DYNAMIC Tue Mar 11 20:03:05 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
7237
tokens/s
220
tokens/s
146
ms
pp4096+tg256
4731
tokens/s
161
tokens/s
872
ms
pp2048+tg256
6015
tokens/s
195
tokens/s
348
ms
pp2048+tg768
6226
tokens/s
188
tokens/s
335
ms
pp1024+tg1024
7309
tokens/s
206
tokens/s
144
ms
pp1280+tg3072
6805
tokens/s
182
tokens/s
193
ms
pp384+tg1152
8259
tokens/s
215
tokens/s
51
ms
pp64+tg1024
6364
tokens/s
223
tokens/s
14
ms
pp16+tg1536
1255
tokens/s
218
tokens/s
17
ms