TEST #322 RESULTS
04/06/2025 - 12:20 AM
ACCELERATOR
MODEL
109
tokens/s
generation
298
ms
time to first token
5147
tokens/s
prompt
1234
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q6_K
SYSTEM
CPU
AMD Ryzen 9 5950X 16-Core Processor (znver3)
RAM
125.7GB
OS
Linux
Kernel Release
6.13.9-200.fc41.x86_64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Sat Mar 29 01:29:31 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
6738
tokens/s
136
tokens/s
159
ms
pp4096+tg256
3458
tokens/s
24.4
tokens/s
1.23
sec
pp2048+tg256
5056
tokens/s
96.4
tokens/s
415
ms
pp2048+tg768
5051
tokens/s
89.7
tokens/s
416
ms
pp1024+tg1024
6472
tokens/s
116
tokens/s
166
ms
pp1280+tg3072
6250
tokens/s
67.0
tokens/s
213
ms
pp384+tg1152
7666
tokens/s
141
tokens/s
56
ms
pp64+tg1024
3685
tokens/s
161
tokens/s
22
ms
pp16+tg1536
1950
tokens/s
148
tokens/s
13
ms