TEST #3312 RESULTS
04/15/2026 - 7:31 AM
ACCELERATOR
MODEL
21.8
tokens/s
generation
2.98
sec
time to first token
490
tokens/s
prompt
153
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 5 5600 6-Core Processor (znver3)
RAM
15.9GB
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
544
tokens/s
26.9
tokens/s
1.92
sec
pp4096+tg256
383
tokens/s
8.6
tokens/s
10.82
sec
pp2048+tg256
477
tokens/s
15.3
tokens/s
4.36
sec
pp2048+tg768
477
tokens/s
13.9
tokens/s
4.36
sec
pp1024+tg1024
533
tokens/s
20.0
tokens/s
1.96
sec
pp1280+tg3072
512
tokens/s
12.1
tokens/s
2.55
sec
pp384+tg1152
583
tokens/s
28.0
tokens/s
681
ms
pp64+tg1024
549
tokens/s
38.8
tokens/s
130
ms
pp16+tg1536
353
tokens/s
32.2
tokens/s
57
ms