TEST #2739 RESULTS
02/18/2026 - 12:10 AM
ACCELERATOR
MODEL
517
tokens/s
generation
49
ms
time to first token
32351
tokens/s
prompt
7012
LocalScore
HOW YOU STACK UP
Explore All ResultsMinueza 2 96M Instruct Variant 03 - Q4_K - Small
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
39528
tokens/s
478
tokens/s
28
ms
pp4096+tg256
20732
tokens/s
473
tokens/s
200
ms
pp2048+tg256
34762
tokens/s
524
tokens/s
61
ms
pp2048+tg768
29247
tokens/s
518
tokens/s
72
ms
pp1024+tg1024
47760
tokens/s
534
tokens/s
23
ms
pp1280+tg3072
44841
tokens/s
509
tokens/s
32
ms
pp384+tg1152
54865
tokens/s
547
tokens/s
9
ms
pp64+tg1024
15497
tokens/s
537
tokens/s
6
ms
pp16+tg1536
3930
tokens/s
533
tokens/s
6
ms