TEST #3010 RESULTS
03/07/2026 - 10:08 PM
ACCELERATOR
MODEL
102
tokens/s
generation
298
ms
time to first token
4778
tokens/s
prompt
1179
LocalScore
HOW YOU STACK UP
Explore All ResultsTitulm Mpt 1b v2.0 - 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
5590
tokens/s
113
tokens/s
192
ms
pp4096+tg256
3804
tokens/s
80.0
tokens/s
1.09
sec
pp2048+tg256
4839
tokens/s
97.8
tokens/s
435
ms
pp2048+tg768
4841
tokens/s
95.0
tokens/s
434
ms
pp1024+tg1024
5626
tokens/s
105
tokens/s
191
ms
pp1280+tg3072
5608
tokens/s
90.9
tokens/s
238
ms
pp384+tg1152
7008
tokens/s
111
tokens/s
64
ms
pp64+tg1024
4311
tokens/s
115
tokens/s
23
ms
pp16+tg1536
1373
tokens/s
113
tokens/s
20
ms