TEST #742 RESULTS
04/19/2025 - 9:20 PM
ACCELERATOR
MODEL
24.4
tokens/s
generation
1.83
sec
time to first token
814
tokens/s
prompt
221
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i7-8750H CPU @ 2.20GHz (skylake)
RAM
31.2GB
OS
Linux
Kernel Release
6.12.10-76061203-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #202412060638~1743109366~22.04~1fce33b SMP PREEMPT_DYNAMIC Thu M
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
903
tokens/s
23.0
tokens/s
1.18
sec
pp4096+tg256
597
tokens/s
17.8
tokens/s
6.92
sec
pp2048+tg256
764
tokens/s
22.4
tokens/s
2.72
sec
pp2048+tg768
878
tokens/s
24.4
tokens/s
2.38
sec
pp1024+tg1024
857
tokens/s
25.0
tokens/s
1.24
sec
pp1280+tg3072
895
tokens/s
22.3
tokens/s
1.47
sec
pp384+tg1152
1058
tokens/s
28.1
tokens/s
397
ms
pp64+tg1024
1011
tokens/s
28.6
tokens/s
97
ms
pp16+tg1536
359
tokens/s
28.0
tokens/s
77
ms