TEST #716 RESULTS
04/14/2025 - 7:27 AM
ACCELERATOR
MODEL
165
tokens/s
generation
256
ms
time to first token
6025
tokens/s
prompt
1572
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 5900X 12-Core Processor (znver3)
RAM
47GB
OS
Linux
Kernel Release
6.13.10-200.fc41.x86_64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Mon Apr 7 19:01:38 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
7133
tokens/s
177
tokens/s
149
ms
pp4096+tg256
4174
tokens/s
138
tokens/s
988
ms
pp2048+tg256
5830
tokens/s
160
tokens/s
357
ms
pp2048+tg768
5372
tokens/s
156
tokens/s
387
ms
pp1024+tg1024
7048
tokens/s
168
tokens/s
151
ms
pp1280+tg3072
6789
tokens/s
155
tokens/s
194
ms
pp384+tg1152
9612
tokens/s
179
tokens/s
45
ms
pp64+tg1024
6353
tokens/s
175
tokens/s
15
ms
pp16+tg1536
1916
tokens/s
176
tokens/s
14
ms