TEST #602 RESULTS
04/08/2025 - 12:57 PM
ACCELERATOR
MODEL
35.0
tokens/s
generation
1.58
sec
time to first token
792
tokens/s
prompt
260
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-8300H CPU @ 2.30GHz (skylake)
RAM
23.9GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1016
tokens/s
41.3
tokens/s
1.03
sec
pp4096+tg256
787
tokens/s
23.9
tokens/s
5.25
sec
pp2048+tg256
913
tokens/s
34.5
tokens/s
2.27
sec
pp2048+tg768
881
tokens/s
32.3
tokens/s
2.35
sec
pp1024+tg1024
910
tokens/s
36.9
tokens/s
1.15
sec
pp1280+tg3072
866
tokens/s
28.1
tokens/s
1.50
sec
pp384+tg1152
882
tokens/s
38.0
tokens/s
461
ms
pp64+tg1024
643
tokens/s
41.5
tokens/s
120
ms
pp16+tg1536
231
tokens/s
38.5
tokens/s
88
ms