TEST #2449 RESULTS
02/01/2026 - 5:55 AM
ACCELERATOR
MODEL
2032
tokens/s
generation
8
ms
time to first token
235917
tokens/s
prompt
38452
LocalScore
HOW YOU STACK UP
Explore All ResultsTiny Gpt2 - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-14450HX (alderlake)
RAM
15.7GB
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
364607
tokens/s
1846
tokens/s
3
ms
pp4096+tg256
156128
tokens/s
1654
tokens/s
27
ms
pp2048+tg256
302118
tokens/s
2001
tokens/s
7
ms
pp2048+tg768
313481
tokens/s
1923
tokens/s
7
ms
pp1024+tg1024
366120
tokens/s
2207
tokens/s
3
ms
pp1280+tg3072
378732
tokens/s
2124
tokens/s
4
ms
pp384+tg1152
214274
tokens/s
2355
tokens/s
2
ms
pp64+tg1024
17496
tokens/s
2027
tokens/s
4
ms
pp16+tg1536
10296
tokens/s
2150
tokens/s
17
ms