TEST #2734 RESULTS
02/18/2026 - 12:07 AM
ACCELERATOR
MODEL
175
tokens/s
generation
563
ms
time to first token
1976
tokens/s
prompt
850
LocalScore
HOW YOU STACK UP
Explore All ResultsMinueza 2 96M Instruct Variant 03 - Q3_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
2744
tokens/s
177
tokens/s
380
ms
pp4096+tg256
2478
tokens/s
173
tokens/s
1.66
sec
pp2048+tg256
2483
tokens/s
174
tokens/s
831
ms
pp2048+tg768
2344
tokens/s
176
tokens/s
880
ms
pp1024+tg1024
2670
tokens/s
177
tokens/s
390
ms
pp1280+tg3072
2645
tokens/s
173
tokens/s
492
ms
pp384+tg1152
1510
tokens/s
175
tokens/s
260
ms
pp64+tg1024
590
tokens/s
171
tokens/s
116
ms
pp16+tg1536
321
tokens/s
177
tokens/s
56
ms