TEST #3003 RESULTS

03/07/2026 - 10:02 PM

704

tokens/s

generation

24

ms

time to first token

59232

tokens/s

prompt

12006

LocalScore

HOW YOU STACK UP
Explore All Results

NexTrim 50M - Q4_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
72266
tokens/s
669
tokens/s
16
ms
pp4096+tg256
44214
tokens/s
616
tokens/s
94
ms
pp2048+tg256
72925
tokens/s
726
tokens/s
29
ms
pp2048+tg768
71176
tokens/s
700
tokens/s
30
ms
pp1024+tg1024
86297
tokens/s
724
tokens/s
13
ms
pp1280+tg3072
85793
tokens/s
688
tokens/s
16
ms
pp384+tg1152
79280
tokens/s
723
tokens/s
7
ms
pp64+tg1024
17044
tokens/s
747
tokens/s
5
ms
pp16+tg1536
4089
tokens/s
744
tokens/s
6
ms