TEST #2795 RESULTS
02/23/2026 - 3:44 AM
ACCELERATOR
MODEL
143
tokens/s
generation
64
ms
time to first token
21525
tokens/s
prompt
3647
LocalScore
HOW YOU STACK UP
Explore All ResultsDMindAI.DMind 3 Nano - 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
26761
tokens/s
143
tokens/s
47
ms
pp4096+tg256
20899
tokens/s
139
tokens/s
204
ms
pp2048+tg256
29546
tokens/s
128
tokens/s
76
ms
pp2048+tg768
21874
tokens/s
144
tokens/s
101
ms
pp1024+tg1024
28175
tokens/s
142
tokens/s
44
ms
pp1280+tg3072
32411
tokens/s
144
tokens/s
46
ms
pp384+tg1152
25512
tokens/s
150
tokens/s
21
ms
pp64+tg1024
6976
tokens/s
149
tokens/s
16
ms
pp16+tg1536
1575
tokens/s
150
tokens/s
18
ms