TEST #3898 RESULTS
07/14/2026 - 2:13 AM
ACCELERATOR
MODEL
45.8
tokens/s
generation
3.51
sec
time to first token
397
tokens/s
prompt
173
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core Ultra 9 275HX (arrowlake-s)
RAM
127.4GB
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
467
tokens/s
43.3
tokens/s
2.22
sec
pp4096+tg256
347
tokens/s
38.6
tokens/s
11.84
sec
pp2048+tg256
380
tokens/s
43.4
tokens/s
5.41
sec
pp2048+tg768
379
tokens/s
43.7
tokens/s
5.43
sec
pp1024+tg1024
422
tokens/s
45.9
tokens/s
2.45
sec
pp1280+tg3072
411
tokens/s
45.0
tokens/s
3.13
sec
pp384+tg1152
442
tokens/s
50.6
tokens/s
887
ms
pp64+tg1024
407
tokens/s
51.3
tokens/s
175
ms
pp16+tg1536
315
tokens/s
50.8
tokens/s
68
ms