TEST #1023 RESULTS
06/09/2025 - 1:23 PM
ACCELERATOR
MODEL
51.5
tokens/s
generation
3.50
sec
time to first token
409
tokens/s
prompt
182
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 9 7900 12-Core Processor (znver4)
RAM
63.1GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
394
tokens/s
53.5
tokens/s
2.62
sec
pp4096+tg256
358
tokens/s
44.3
tokens/s
11.47
sec
pp2048+tg256
406
tokens/s
49.9
tokens/s
5.07
sec
pp2048+tg768
406
tokens/s
48.8
tokens/s
5.07
sec
pp1024+tg1024
434
tokens/s
51.4
tokens/s
2.38
sec
pp1280+tg3072
336
tokens/s
47.3
tokens/s
3.83
sec
pp384+tg1152
456
tokens/s
53.1
tokens/s
861
ms
pp64+tg1024
466
tokens/s
56.8
tokens/s
153
ms
pp16+tg1536
428
tokens/s
58.0
tokens/s
54
ms