TEST #1404 RESULTS
08/20/2025 - 1:38 PM
ACCELERATOR
MODEL
123
tokens/s
generation
401
ms
time to first token
3665
tokens/s
prompt
1040
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
12th Gen Intel Core i5-12600HX (alderlake)
RAM
31GB
OS
Linux
Kernel Release
6.12.33+kali-amd64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Kali 6.12.33-1kali1 (2025-06-25)
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
4223
tokens/s
142
tokens/s
250
ms
pp4096+tg256
2757
tokens/s
103
tokens/s
1.50
sec
pp2048+tg256
3593
tokens/s
121
tokens/s
578
ms
pp2048+tg768
3606
tokens/s
117
tokens/s
576
ms
pp1024+tg1024
4174
tokens/s
126
tokens/s
252
ms
pp1280+tg3072
3883
tokens/s
111
tokens/s
337
ms
pp384+tg1152
4858
tokens/s
127
tokens/s
86
ms
pp64+tg1024
4760
tokens/s
132
tokens/s
19
ms
pp16+tg1536
1128
tokens/s
129
tokens/s
20
ms