TEST #585 RESULTS
04/08/2025 - 11:07 AM
ACCELERATOR
MODEL
79.4
tokens/s
generation
1.24
sec
time to first token
1019
tokens/s
prompt
403
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 3B Instruct - Q3_K - Large
SYSTEM
CPU
AMD Ryzen 9 5950X 16-Core Processor (znver3)
RAM
62.7GB
OS
Linux
Kernel Release
6.14.1-1-cachyos
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Tue, 08 Apr 2025 06:33:52 +0000
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1157
tokens/s
92.8
tokens/s
895
ms
pp4096+tg256
1024
tokens/s
43.8
tokens/s
4.02
sec
pp2048+tg256
1106
tokens/s
66.6
tokens/s
1.87
sec
pp2048+tg768
1111
tokens/s
62.4
tokens/s
1.86
sec
pp1024+tg1024
1158
tokens/s
79.4
tokens/s
895
ms
pp1280+tg3072
1139
tokens/s
57.4
tokens/s
1.14
sec
pp384+tg1152
1152
tokens/s
96.1
tokens/s
342
ms
pp64+tg1024
700
tokens/s
113
tokens/s
99
ms
pp16+tg1536
623
tokens/s
103
tokens/s
32
ms