TEST #725 RESULTS
04/15/2025 - 5:04 AM
ACCELERATOR
MODEL
25.7
tokens/s
generation
19.03
sec
time to first token
75
tokens/s
prompt
47
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core Ultra 7 155U (alderlake)
RAM
62.3GB
OS
Linux
Kernel Release
6.13.10-200.fc41.x86_64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Mon Apr 7 19:01:38 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
83
tokens/s
31.3
tokens/s
12.33
sec
pp4096+tg256
64
tokens/s
18.4
tokens/s
64.17
sec
pp2048+tg256
72
tokens/s
25.3
tokens/s
28.37
sec
pp2048+tg768
68
tokens/s
24.2
tokens/s
30.02
sec
pp1024+tg1024
77
tokens/s
26.6
tokens/s
13.37
sec
pp1280+tg3072
76
tokens/s
21.0
tokens/s
16.92
sec
pp384+tg1152
78
tokens/s
26.5
tokens/s
4.98
sec
pp64+tg1024
80
tokens/s
29.3
tokens/s
831
ms
pp16+tg1536
76
tokens/s
28.3
tokens/s
241
ms