TEST #2373 RESULTS
01/30/2026 - 12:06 PM
ACCELERATOR
MODEL
132
tokens/s
generation
285
ms
time to first token
5332
tokens/s
prompt
1353
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-14450HX (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
6516
tokens/s
138
tokens/s
165
ms
pp4096+tg256
3762
tokens/s
116
tokens/s
1.10
sec
pp2048+tg256
5135
tokens/s
131
tokens/s
408
ms
pp2048+tg768
5178
tokens/s
128
tokens/s
403
ms
pp1024+tg1024
6149
tokens/s
135
tokens/s
174
ms
pp1280+tg3072
5974
tokens/s
125
tokens/s
222
ms
pp384+tg1152
9236
tokens/s
139
tokens/s
49
ms
pp64+tg1024
5304
tokens/s
140
tokens/s
19
ms
pp16+tg1536
734
tokens/s
140
tokens/s
29
ms