TEST #2729 RESULTS
02/18/2026 - 12:01 AM
ACCELERATOR
MODEL
239
tokens/s
generation
60
ms
time to first token
23089
tokens/s
prompt
4516
LocalScore
HOW YOU STACK UP
Explore All ResultsMinueza 2 96M Instruct Variant 03 - BF16
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
30857
tokens/s
239
tokens/s
38
ms
pp4096+tg256
19558
tokens/s
229
tokens/s
214
ms
pp2048+tg256
28035
tokens/s
239
tokens/s
77
ms
pp2048+tg768
27943
tokens/s
238
tokens/s
77
ms
pp1024+tg1024
34107
tokens/s
240
tokens/s
34
ms
pp1280+tg3072
26270
tokens/s
238
tokens/s
53
ms
pp384+tg1152
33393
tokens/s
242
tokens/s
16
ms
pp64+tg1024
6376
tokens/s
243
tokens/s
14
ms
pp16+tg1536
1263
tokens/s
244
tokens/s
17
ms