TEST #1202 RESULTS
07/09/2025 - 4:52 AM
ACCELERATOR
MODEL
11.8
tokens/s
generation
38.98
sec
time to first token
34
tokens/s
prompt
22
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
13th Gen Intel Core i5-1335U (alderlake)
RAM
63.2GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
40
tokens/s
12.9
tokens/s
25.87
sec
pp4096+tg256
34
tokens/s
9.1
tokens/s
121.73
sec
pp2048+tg256
35
tokens/s
11.1
tokens/s
58.31
sec
pp2048+tg768
31
tokens/s
10.9
tokens/s
66.62
sec
pp1024+tg1024
36
tokens/s
12.0
tokens/s
28.67
sec
pp1280+tg3072
34
tokens/s
10.5
tokens/s
37.19
sec
pp384+tg1152
42
tokens/s
12.8
tokens/s
9.24
sec
pp64+tg1024
27
tokens/s
13.4
tokens/s
2.46
sec
pp16+tg1536
23
tokens/s
13.2
tokens/s
748
ms