TEST #235 RESULTS
04/04/2025 - 6:28 PM
ACCELERATOR
MODEL
7.7
tokens/s
generation
49.20
sec
time to first token
30
tokens/s
prompt
17
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i7-8550U CPU @ 1.80GHz (skylake)
RAM
15.5GB
OS
Linux
Kernel Release
6.8.0-57-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #59-Ubuntu SMP PREEMPT_DYNAMIC Sat Mar 15 17:40:59 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
30
tokens/s
8.5
tokens/s
34.22
sec
pp4096+tg256
24
tokens/s
5.9
tokens/s
171.21
sec
pp2048+tg256
28
tokens/s
7.4
tokens/s
73.20
sec
pp2048+tg768
28
tokens/s
7.1
tokens/s
73.18
sec
pp1024+tg1024
31
tokens/s
7.9
tokens/s
33.60
sec
pp1280+tg3072
30
tokens/s
6.8
tokens/s
42.89
sec
pp384+tg1152
33
tokens/s
8.5
tokens/s
11.81
sec
pp64+tg1024
34
tokens/s
8.8
tokens/s
2.00
sec
pp16+tg1536
30
tokens/s
8.3
tokens/s
649
ms