TEST #3144 RESULTS
03/21/2026 - 6:11 PM
ACCELERATOR
MODEL
176
tokens/s
generation
175
ms
time to first token
8835
tokens/s
prompt
2073
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
10908
tokens/s
179
tokens/s
100
ms
pp4096+tg256
5940
tokens/s
165
tokens/s
696
ms
pp2048+tg256
8559
tokens/s
168
tokens/s
245
ms
pp2048+tg768
8573
tokens/s
176
tokens/s
245
ms
pp1024+tg1024
11103
tokens/s
178
tokens/s
98
ms
pp1280+tg3072
10434
tokens/s
173
tokens/s
128
ms
pp384+tg1152
14899
tokens/s
180
tokens/s
31
ms
pp64+tg1024
6998
tokens/s
182
tokens/s
15
ms
pp16+tg1536
2101
tokens/s
182
tokens/s
13
ms