TEST #3147 RESULTS
03/21/2026 - 8:27 PM
ACCELERATOR
MODEL
176
tokens/s
generation
179
ms
time to first token
8411
tokens/s
prompt
2025
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-14400F (alderlake)
RAM
15.8GB
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
11121
tokens/s
176
tokens/s
98
ms
pp4096+tg256
5973
tokens/s
165
tokens/s
692
ms
pp2048+tg256
8605
tokens/s
175
tokens/s
244
ms
pp2048+tg768
8663
tokens/s
178
tokens/s
242
ms
pp1024+tg1024
11094
tokens/s
175
tokens/s
98
ms
pp1280+tg3072
8803
tokens/s
173
tokens/s
151
ms
pp384+tg1152
13995
tokens/s
181
tokens/s
33
ms
pp64+tg1024
6931
tokens/s
181
tokens/s
15
ms
pp16+tg1536
519
tokens/s
182
tokens/s
37
ms