TEST #2570 RESULTS
02/10/2026 - 9:01 AM
ACCELERATOR
MODEL
75.8
tokens/s
generation
1.09
sec
time to first token
1053
tokens/s
prompt
418
LocalScore
HOW YOU STACK UP
Explore All ResultsMiniPLM Mamba 130M - 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
1320
tokens/s
81.3
tokens/s
791
ms
pp4096+tg256
1309
tokens/s
82.1
tokens/s
3.14
sec
pp2048+tg256
1204
tokens/s
69.7
tokens/s
1.72
sec
pp2048+tg768
1184
tokens/s
71.2
tokens/s
1.76
sec
pp1024+tg1024
1242
tokens/s
74.6
tokens/s
841
ms
pp1280+tg3072
1263
tokens/s
74.8
tokens/s
1.03
sec
pp384+tg1152
1164
tokens/s
76.2
tokens/s
345
ms
pp64+tg1024
578
tokens/s
75.4
tokens/s
127
ms
pp16+tg1536
212
tokens/s
76.5
tokens/s
89
ms