TEST #3218 RESULTS
03/31/2026 - 1:56 PM
ACCELERATOR
MODEL
94.1
tokens/s
generation
350
ms
time to first token
4127
tokens/s
prompt
1035
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
13th Gen Intel Core i5-13500H (alderlake)
RAM
15.6GB
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
5354
tokens/s
110
tokens/s
200
ms
pp4096+tg256
3232
tokens/s
82.4
tokens/s
1.28
sec
pp2048+tg256
4297
tokens/s
103
tokens/s
488
ms
pp2048+tg768
4045
tokens/s
85.3
tokens/s
519
ms
pp1024+tg1024
4948
tokens/s
89.8
tokens/s
219
ms
pp1280+tg3072
4713
tokens/s
85.6
tokens/s
284
ms
pp384+tg1152
7856
tokens/s
94.7
tokens/s
60
ms
pp64+tg1024
2419
tokens/s
99.1
tokens/s
36
ms
pp16+tg1536
280
tokens/s
96.9
tokens/s
67
ms