TEST #2733 RESULTS
02/18/2026 - 12:06 AM
ACCELERATOR
MODEL
172
tokens/s
generation
564
ms
time to first token
2096
tokens/s
prompt
861
LocalScore
HOW YOU STACK UP
Explore All ResultsMinueza 2 96M Instruct Variant 03 - Q3_K - Large
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
2633
tokens/s
182
tokens/s
395
ms
pp4096+tg256
2527
tokens/s
166
tokens/s
1.63
sec
pp2048+tg256
2574
tokens/s
173
tokens/s
801
ms
pp2048+tg768
2465
tokens/s
172
tokens/s
842
ms
pp1024+tg1024
2225
tokens/s
168
tokens/s
466
ms
pp1280+tg3072
2276
tokens/s
172
tokens/s
568
ms
pp384+tg1152
1516
tokens/s
165
tokens/s
259
ms
pp64+tg1024
2436
tokens/s
175
tokens/s
33
ms
pp16+tg1536
208
tokens/s
174
tokens/s
83
ms