TEST #1400 RESULTS
08/20/2025 - 12:10 PM
ACCELERATOR
MODEL
21.6
tokens/s
generation
17.90
sec
time to first token
80
tokens/s
prompt
46
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i7-8565U CPU @ 1.80GHz (skylake)
RAM
31.2GB
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
83
tokens/s
22.3
tokens/s
12.40
sec
pp4096+tg256
66
tokens/s
17.2
tokens/s
62.06
sec
pp2048+tg256
78
tokens/s
20.7
tokens/s
26.33
sec
pp2048+tg768
76
tokens/s
20.3
tokens/s
26.91
sec
pp1024+tg1024
85
tokens/s
22.1
tokens/s
12.15
sec
pp1280+tg3072
80
tokens/s
19.5
tokens/s
15.98
sec
pp384+tg1152
91
tokens/s
23.6
tokens/s
4.25
sec
pp64+tg1024
89
tokens/s
24.5
tokens/s
760
ms
pp16+tg1536
74
tokens/s
23.9
tokens/s
253
ms