TEST #2314 RESULTS
01/16/2026 - 2:45 PM
ACCELERATOR
MODEL
92.7
tokens/s
generation
3.35
sec
time to first token
417
tokens/s
prompt
226
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Intel Core Ultra 7 265K (arrowlake-s)
RAM
31.4GB
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
445
tokens/s
97.6
tokens/s
2.31
sec
pp4096+tg256
357
tokens/s
80.2
tokens/s
11.50
sec
pp2048+tg256
411
tokens/s
89.1
tokens/s
4.99
sec
pp2048+tg768
412
tokens/s
88.6
tokens/s
4.98
sec
pp1024+tg1024
442
tokens/s
93.8
tokens/s
2.33
sec
pp1280+tg3072
436
tokens/s
86.4
tokens/s
2.94
sec
pp384+tg1152
460
tokens/s
97.9
tokens/s
845
ms
pp64+tg1024
433
tokens/s
101
tokens/s
157
ms
pp16+tg1536
359
tokens/s
100
tokens/s
54
ms