TEST #529 RESULTS
04/07/2025 - 9:12 PM
ACCELERATOR
MODEL
97.3
tokens/s
generation
223
ms
time to first token
6259
tokens/s
prompt
1397
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen AI 9 HX 370 w/ Radeon 890M
RAM
30.5GB
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
7992
tokens/s
110
tokens/s
138
ms
pp4096+tg256
5295
tokens/s
74.0
tokens/s
788
ms
pp2048+tg256
6672
tokens/s
89.1
tokens/s
319
ms
pp2048+tg768
6343
tokens/s
89.6
tokens/s
335
ms
pp1024+tg1024
7956
tokens/s
98.5
tokens/s
139
ms
pp1280+tg3072
7392
tokens/s
85.6
tokens/s
184
ms
pp384+tg1152
9939
tokens/s
106
tokens/s
50
ms
pp64+tg1024
4102
tokens/s
113
tokens/s
24
ms
pp16+tg1536
641
tokens/s
110
tokens/s
33
ms