TEST #2736 RESULTS
02/18/2026 - 12:09 AM
ACCELERATOR
MODEL
522
tokens/s
generation
45
ms
time to first token
34113
tokens/s
prompt
7334
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
40214
tokens/s
459
tokens/s
28
ms
pp4096+tg256
22305
tokens/s
476
tokens/s
186
ms
pp2048+tg256
35430
tokens/s
535
tokens/s
60
ms
pp2048+tg768
35573
tokens/s
520
tokens/s
60
ms
pp1024+tg1024
48229
tokens/s
537
tokens/s
23
ms
pp1280+tg3072
46571
tokens/s
509
tokens/s
29
ms
pp384+tg1152
57412
tokens/s
543
tokens/s
9
ms
pp64+tg1024
16255
tokens/s
565
tokens/s
6
ms
pp16+tg1536
5025
tokens/s
551
tokens/s
5
ms