TEST #1266 RESULTS
07/28/2025 - 11:12 PM
ACCELERATOR
MODEL
11.5
tokens/s
generation
2.09
sec
time to first token
617
tokens/s
prompt
150
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 7840U w/ Radeon 780M Graphics (znver4)
RAM
55.8GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
764
tokens/s
11.8
tokens/s
1.43
sec
pp4096+tg256
596
tokens/s
3.6
tokens/s
7.15
sec
pp2048+tg256
718
tokens/s
8.4
tokens/s
2.99
sec
pp2048+tg768
714
tokens/s
7.5
tokens/s
3.00
sec
pp1024+tg1024
741
tokens/s
10.8
tokens/s
1.46
sec
pp1280+tg3072
700
tokens/s
6.4
tokens/s
1.93
sec
pp384+tg1152
776
tokens/s
15.6
tokens/s
542
ms
pp64+tg1024
312
tokens/s
21.2
tokens/s
233
ms
pp16+tg1536
235
tokens/s
17.8
tokens/s
98
ms