TEST #2508 RESULTS
02/01/2026 - 11:27 PM
ACCELERATOR
MODEL
94.2
tokens/s
generation
278
ms
time to first token
5652
tokens/s
prompt
1241
LocalScore
HOW YOU STACK UP
Explore All ResultsNusantara 0.8b Indo Chat - 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
7380
tokens/s
104
tokens/s
148
ms
pp4096+tg256
3763
tokens/s
79.9
tokens/s
1.10
sec
pp2048+tg256
5396
tokens/s
95.1
tokens/s
392
ms
pp2048+tg768
5396
tokens/s
91.4
tokens/s
391
ms
pp1024+tg1024
7360
tokens/s
98.5
tokens/s
149
ms
pp1280+tg3072
6476
tokens/s
88.8
tokens/s
207
ms
pp384+tg1152
9471
tokens/s
95.6
tokens/s
50
ms
pp64+tg1024
4460
tokens/s
97.4
tokens/s
38
ms
pp16+tg1536
1162
tokens/s
96.4
tokens/s
27
ms