TEST #1345 RESULTS
08/09/2025 - 12:35 AM
ACCELERATOR
MODEL
77.0
tokens/s
generation
552
ms
time to first token
3504
tokens/s
prompt
788
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-9500 CPU @ 3.00GHz (skylake)
RAM
79.9GB
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
4006
tokens/s
88.4
tokens/s
267
ms
pp4096+tg256
1703
tokens/s
59.0
tokens/s
2.42
sec
pp2048+tg256
2671
tokens/s
57.4
tokens/s
784
ms
pp2048+tg768
2769
tokens/s
52.7
tokens/s
756
ms
pp1024+tg1024
3979
tokens/s
71.6
tokens/s
268
ms
pp1280+tg3072
3641
tokens/s
51.1
tokens/s
365
ms
pp384+tg1152
6426
tokens/s
93.7
tokens/s
68
ms
pp64+tg1024
4829
tokens/s
116
tokens/s
19
ms
pp16+tg1536
1514
tokens/s
103
tokens/s
17
ms