TEST #3278 RESULTS
04/10/2026 - 9:09 PM
ACCELERATOR
MODEL
132
tokens/s
generation
282
ms
time to first token
5231
tokens/s
prompt
1349
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
12th Gen Intel Core i5-12500H (alderlake)
RAM
15.7GB
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
6414
tokens/s
136
tokens/s
167
ms
pp4096+tg256
3779
tokens/s
118
tokens/s
1.09
sec
pp2048+tg256
5243
tokens/s
131
tokens/s
398
ms
pp2048+tg768
5200
tokens/s
131
tokens/s
402
ms
pp1024+tg1024
6392
tokens/s
135
tokens/s
168
ms
pp1280+tg3072
6169
tokens/s
127
tokens/s
215
ms
pp384+tg1152
8839
tokens/s
137
tokens/s
51
ms
pp64+tg1024
3499
tokens/s
139
tokens/s
25
ms
pp16+tg1536
1545
tokens/s
138
tokens/s
17
ms