TEST #326 RESULTS
04/06/2025 - 12:32 AM
ACCELERATOR
MODEL
29.1
tokens/s
generation
911
ms
time to first token
1475
tokens/s
prompt
361
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 3B Instruct - F16
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
2014
tokens/s
34.6
tokens/s
538
ms
pp4096+tg256
1234
tokens/s
9.0
tokens/s
3.43
sec
pp2048+tg256
1687
tokens/s
29.0
tokens/s
1.25
sec
pp2048+tg768
1690
tokens/s
27.8
tokens/s
1.25
sec
pp1024+tg1024
1972
tokens/s
31.6
tokens/s
548
ms
pp1280+tg3072
1848
tokens/s
22.5
tokens/s
723
ms
pp384+tg1152
2086
tokens/s
34.6
tokens/s
210
ms
pp64+tg1024
579
tokens/s
37.2
tokens/s
135
ms
pp16+tg1536
162
tokens/s
35.9
tokens/s
123
ms