TEST #2495 RESULTS
02/01/2026 - 10:50 AM
ACCELERATOR
MODEL
163
tokens/s
generation
60
ms
time to first token
23265
tokens/s
prompt
3987
LocalScore
HOW YOU STACK UP
Explore All ResultsDogeAI v1.5 Coder - 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
27591
tokens/s
160
tokens/s
46
ms
pp4096+tg256
20718
tokens/s
162
tokens/s
204
ms
pp2048+tg256
29995
tokens/s
163
tokens/s
76
ms
pp2048+tg768
29980
tokens/s
163
tokens/s
76
ms
pp1024+tg1024
34651
tokens/s
162
tokens/s
35
ms
pp1280+tg3072
30638
tokens/s
161
tokens/s
48
ms
pp384+tg1152
27410
tokens/s
164
tokens/s
23
ms
pp64+tg1024
6928
tokens/s
169
tokens/s
15
ms
pp16+tg1536
1477
tokens/s
165
tokens/s
18
ms