TEST #3143 RESULTS
03/21/2026 - 6:09 PM
ACCELERATOR
MODEL
174
tokens/s
generation
177
ms
time to first token
8575
tokens/s
prompt
2036
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
11136
tokens/s
174
tokens/s
98
ms
pp4096+tg256
5965
tokens/s
164
tokens/s
693
ms
pp2048+tg256
8553
tokens/s
175
tokens/s
245
ms
pp2048+tg768
8072
tokens/s
171
tokens/s
259
ms
pp1024+tg1024
10997
tokens/s
175
tokens/s
100
ms
pp1280+tg3072
9902
tokens/s
172
tokens/s
135
ms
pp384+tg1152
14666
tokens/s
176
tokens/s
32
ms
pp64+tg1024
6336
tokens/s
179
tokens/s
16
ms
pp16+tg1536
1552
tokens/s
181
tokens/s
16
ms