TEST #3399 RESULTS
04/27/2026 - 4:45 AM
ACCELERATOR
MODEL
10.4
tokens/s
generation
2.81
sec
time to first token
480
tokens/s
prompt
121
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 5 8600G w/ Radeon 760M Graphics (znver4)
RAM
31.1GB
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
566
tokens/s
11.3
tokens/s
1.90
sec
pp4096+tg256
407
tokens/s
3.5
tokens/s
10.35
sec
pp2048+tg256
535
tokens/s
7.7
tokens/s
3.97
sec
pp2048+tg768
536
tokens/s
7.1
tokens/s
3.96
sec
pp1024+tg1024
605
tokens/s
10.1
tokens/s
1.78
sec
pp1280+tg3072
579
tokens/s
6.1
tokens/s
2.31
sec
pp384+tg1152
639
tokens/s
13.8
tokens/s
651
ms
pp64+tg1024
251
tokens/s
18.3
tokens/s
289
ms
pp16+tg1536
201
tokens/s
15.5
tokens/s
116
ms