TEST #542 RESULTS
04/07/2025 - 11:04 PM
ACCELERATOR
MODEL
16.0
tokens/s
generation
417
ms
time to first token
3734
tokens/s
prompt
523
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 7950X 16-Core Processor (znver4)
RAM
62.2GB
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
5428
tokens/s
17.1
tokens/s
247
ms
pp4096+tg256
3183
tokens/s
4.6
tokens/s
1.50
sec
pp2048+tg256
4228
tokens/s
11.4
tokens/s
586
ms
pp2048+tg768
4240
tokens/s
10.4
tokens/s
585
ms
pp1024+tg1024
5179
tokens/s
15.1
tokens/s
257
ms
pp1280+tg3072
4460
tokens/s
8.6
tokens/s
357
ms
pp384+tg1152
4918
tokens/s
21.6
tokens/s
110
ms
pp64+tg1024
1384
tokens/s
30.3
tokens/s
64
ms
pp16+tg1536
590
tokens/s
24.7
tokens/s
43
ms