TEST #332 RESULTS
04/06/2025 - 12:47 AM
ACCELERATOR
MODEL
55.3
tokens/s
generation
705
ms
time to first token
2159
tokens/s
prompt
554
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 3B Instruct - Q4_K - Medium
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
2738
tokens/s
70.2
tokens/s
388
ms
pp4096+tg256
1466
tokens/s
10.3
tokens/s
2.89
sec
pp2048+tg256
2166
tokens/s
50.4
tokens/s
965
ms
pp2048+tg768
2166
tokens/s
47.0
tokens/s
965
ms
pp1024+tg1024
2660
tokens/s
59.1
tokens/s
399
ms
pp1280+tg3072
2521
tokens/s
33.4
tokens/s
524
ms
pp384+tg1152
3134
tokens/s
70.2
tokens/s
134
ms
pp64+tg1024
1638
tokens/s
81.7
tokens/s
49
ms
pp16+tg1536
945
tokens/s
75.9
tokens/s
27
ms