TEST #2618 RESULTS
02/14/2026 - 11:32 AM
ACCELERATOR
MODEL
459
tokens/s
generation
47
ms
time to first token
33267
tokens/s
prompt
6860
LocalScore
HOW YOU STACK UP
Explore All ResultsMinueza 2 96M Instruct Variant 03 - Q4_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
38328
tokens/s
344
tokens/s
30
ms
pp4096+tg256
20634
tokens/s
398
tokens/s
202
ms
pp2048+tg256
35436
tokens/s
443
tokens/s
60
ms
pp2048+tg768
35031
tokens/s
476
tokens/s
61
ms
pp1024+tg1024
48131
tokens/s
481
tokens/s
23
ms
pp1280+tg3072
45394
tokens/s
478
tokens/s
30
ms
pp384+tg1152
56681
tokens/s
487
tokens/s
9
ms
pp64+tg1024
15400
tokens/s
514
tokens/s
6
ms
pp16+tg1536
4367
tokens/s
510
tokens/s
6
ms