TEST #2744 RESULTS
02/18/2026 - 12:11 AM
ACCELERATOR
MODEL
509
tokens/s
generation
47
ms
time to first token
33036
tokens/s
prompt
7105
LocalScore
HOW YOU STACK UP
Explore All ResultsMinueza 2 96M Instruct Variant 03 - Q8_0
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
39122
tokens/s
500
tokens/s
28
ms
pp4096+tg256
21210
tokens/s
481
tokens/s
195
ms
pp2048+tg256
34390
tokens/s
533
tokens/s
61
ms
pp2048+tg768
34711
tokens/s
507
tokens/s
62
ms
pp1024+tg1024
47979
tokens/s
510
tokens/s
23
ms
pp1280+tg3072
44738
tokens/s
495
tokens/s
32
ms
pp384+tg1152
54535
tokens/s
508
tokens/s
9
ms
pp64+tg1024
16373
tokens/s
530
tokens/s
6
ms
pp16+tg1536
4268
tokens/s
519
tokens/s
6
ms