TEST #651 RESULTS
04/09/2025 - 7:07 PM
ACCELERATOR
MODEL
12.3
tokens/s
generation
522
ms
time to first token
3646
tokens/s
prompt
442
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 7800X3D 8-Core Processor (znver4)
RAM
31.6GB
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
5118
tokens/s
12.4
tokens/s
274
ms
pp4096+tg256
2121
tokens/s
3.7
tokens/s
2.19
sec
pp2048+tg256
3640
tokens/s
8.7
tokens/s
696
ms
pp2048+tg768
3669
tokens/s
7.8
tokens/s
689
ms
pp1024+tg1024
5087
tokens/s
11.7
tokens/s
276
ms
pp1280+tg3072
4315
tokens/s
6.6
tokens/s
386
ms
pp384+tg1152
5603
tokens/s
17.1
tokens/s
108
ms
pp64+tg1024
2469
tokens/s
23.6
tokens/s
45
ms
pp16+tg1536
791
tokens/s
19.4
tokens/s
36
ms