TEST #2731 RESULTS

02/18/2026 - 12:03 AM

125

tokens/s

generation

738

ms

time to first token

1483

tokens/s

prompt

631

LocalScore

HOW YOU STACK UP
Explore All Results

Minueza 2 96M Instruct Variant 03 - IQ4_XS - 4.25 bpw

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
2047
tokens/s
124
tokens/s
508
ms
pp4096+tg256
2002
tokens/s
125
tokens/s
2.05
sec
pp2048+tg256
1883
tokens/s
127
tokens/s
1.09
sec
pp2048+tg768
1923
tokens/s
129
tokens/s
1.07
sec
pp1024+tg1024
1813
tokens/s
125
tokens/s
574
ms
pp1280+tg3072
1729
tokens/s
122
tokens/s
748
ms
pp384+tg1152
1440
tokens/s
126
tokens/s
278
ms
pp64+tg1024
379
tokens/s
125
tokens/s
176
ms
pp16+tg1536
127
tokens/s
125
tokens/s
136
ms