TEST #731 RESULTS
04/17/2025 - 8:26 AM
ACCELERATOR
MODEL
109
tokens/s
generation
416
ms
time to first token
3399
tokens/s
prompt
962
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
12th Gen Intel Core i7-12700H (alderlake)
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
4117
tokens/s
112
tokens/s
257
ms
pp4096+tg256
2667
tokens/s
93.4
tokens/s
1.55
sec
pp2048+tg256
3481
tokens/s
106
tokens/s
598
ms
pp2048+tg768
3482
tokens/s
105
tokens/s
598
ms
pp1024+tg1024
4130
tokens/s
111
tokens/s
257
ms
pp1280+tg3072
3877
tokens/s
102
tokens/s
339
ms
pp384+tg1152
4717
tokens/s
116
tokens/s
91
ms
pp64+tg1024
3487
tokens/s
118
tokens/s
27
ms
pp16+tg1536
631
tokens/s
117
tokens/s
33
ms