TEST #3102 RESULTS
03/17/2026 - 9:51 AM
ACCELERATOR
MODEL
58.8
tokens/s
generation
7.56
sec
time to first token
308
tokens/s
prompt
134
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-14600K (alderlake)
RAM
31.7GB
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
184
tokens/s
51.7
tokens/s
5.58
sec
pp4096+tg256
149
tokens/s
42.4
tokens/s
27.57
sec
pp2048+tg256
131
tokens/s
34.4
tokens/s
17.78
sec
pp2048+tg768
202
tokens/s
62.1
tokens/s
10.16
sec
pp1024+tg1024
404
tokens/s
66.6
tokens/s
2.54
sec
pp1280+tg3072
389
tokens/s
61.1
tokens/s
3.31
sec
pp384+tg1152
430
tokens/s
69.0
tokens/s
909
ms
pp64+tg1024
471
tokens/s
71.9
tokens/s
148
ms
pp16+tg1536
416
tokens/s
69.9
tokens/s
50
ms