TEST #605 RESULTS
04/08/2025 - 3:03 PM
ACCELERATOR
MODEL
92.5
tokens/s
generation
510
ms
time to first token
3054
tokens/s
prompt
821
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 5700X 8-Core Processor (znver3)
RAM
31.3GB
OS
Linux
Kernel Release
6.13.8-200.fc41.x86_64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Sun Mar 23 05:03:09 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
3694
tokens/s
117
tokens/s
286
ms
pp4096+tg256
2050
tokens/s
14.6
tokens/s
2.07
sec
pp2048+tg256
2918
tokens/s
83.0
tokens/s
714
ms
pp2048+tg768
2913
tokens/s
77.7
tokens/s
715
ms
pp1024+tg1024
3678
tokens/s
98.8
tokens/s
287
ms
pp1280+tg3072
3442
tokens/s
52.2
tokens/s
381
ms
pp384+tg1152
4321
tokens/s
119
tokens/s
96
ms
pp64+tg1024
2846
tokens/s
141
tokens/s
28
ms
pp16+tg1536
1628
tokens/s
129
tokens/s
15
ms