TEST #1660 RESULTS
10/16/2025 - 8:08 PM
ACCELERATOR
MODEL
122
tokens/s
generation
71
ms
time to first token
18272
tokens/s
prompt
3146
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD RYZEN AI MAX+ 395 w/ Radeon 8060S
RAM
93.9GB
OS
Linux
Kernel Release
6.17.1-200.nobara.fc42.x86_64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Mon Oct 6 20:42:25 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
25014
tokens/s
135
tokens/s
48
ms
pp4096+tg256
20020
tokens/s
99.8
tokens/s
215
ms
pp2048+tg256
22442
tokens/s
121
tokens/s
100
ms
pp2048+tg768
22420
tokens/s
112
tokens/s
100
ms
pp1024+tg1024
24981
tokens/s
126
tokens/s
49
ms
pp1280+tg3072
22385
tokens/s
108
tokens/s
65
ms
pp384+tg1152
21580
tokens/s
130
tokens/s
26
ms
pp64+tg1024
4408
tokens/s
132
tokens/s
21
ms
pp16+tg1536
1197
tokens/s
132
tokens/s
20
ms