TEST #1050 RESULTS
06/14/2025 - 2:42 AM
ACCELERATOR
MODEL
57.1
tokens/s
generation
903
ms
time to first token
1502
tokens/s
prompt
456
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
13th Gen Intel Core i5-13500HX (alderlake)
RAM
31.7GB
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
1859
tokens/s
63.2
tokens/s
568
ms
pp4096+tg256
1273
tokens/s
38.2
tokens/s
3.24
sec
pp2048+tg256
1586
tokens/s
52.0
tokens/s
1.31
sec
pp2048+tg768
1570
tokens/s
49.5
tokens/s
1.32
sec
pp1024+tg1024
1801
tokens/s
59.0
tokens/s
586
ms
pp1280+tg3072
1712
tokens/s
46.8
tokens/s
765
ms
pp384+tg1152
1939
tokens/s
64.5
tokens/s
214
ms
pp64+tg1024
843
tokens/s
72.1
tokens/s
88
ms
pp16+tg1536
934
tokens/s
68.6
tokens/s
29
ms