TEST #1585 RESULTS
10/05/2025 - 9:18 AM
ACCELERATOR
MODEL
35.9
tokens/s
generation
11.49
sec
time to first token
124
tokens/s
prompt
73
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core Ultra 5 225H (arrowlake)
RAM
30.7GB
OS
Linux
Kernel Release
6.8.0-85-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #85-Ubuntu SMP PREEMPT_DYNAMIC Thu Sep 18 15:26:59 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
133
tokens/s
38.7
tokens/s
7.71
sec
pp4096+tg256
105
tokens/s
29.7
tokens/s
38.98
sec
pp2048+tg256
120
tokens/s
34.8
tokens/s
17.14
sec
pp2048+tg768
119
tokens/s
33.8
tokens/s
17.23
sec
pp1024+tg1024
126
tokens/s
36.6
tokens/s
8.16
sec
pp1280+tg3072
122
tokens/s
32.8
tokens/s
10.56
sec
pp384+tg1152
129
tokens/s
38.5
tokens/s
3.00
sec
pp64+tg1024
133
tokens/s
39.8
tokens/s
505
ms
pp16+tg1536
126
tokens/s
38.8
tokens/s
150
ms