TEST #2738 RESULTS
02/18/2026 - 12:09 AM
ACCELERATOR
MODEL
513
tokens/s
generation
48
ms
time to first token
32676
tokens/s
prompt
7048
LocalScore
HOW YOU STACK UP
Explore All ResultsMinueza 2 96M Instruct Variant 03 - 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
38384
tokens/s
441
tokens/s
30
ms
pp4096+tg256
21969
tokens/s
467
tokens/s
190
ms
pp2048+tg256
33716
tokens/s
531
tokens/s
64
ms
pp2048+tg768
28699
tokens/s
530
tokens/s
73
ms
pp1024+tg1024
49004
tokens/s
525
tokens/s
23
ms
pp1280+tg3072
45854
tokens/s
508
tokens/s
30
ms
pp384+tg1152
57027
tokens/s
534
tokens/s
9
ms
pp64+tg1024
15601
tokens/s
542
tokens/s
6
ms
pp16+tg1536
3832
tokens/s
542
tokens/s
7
ms