TEST #2423 RESULTS
01/31/2026 - 3:31 PM
ACCELERATOR
MODEL
82.1
tokens/s
generation
316
ms
time to first token
4476
tokens/s
prompt
1052
LocalScore
HOW YOU STACK UP
Explore All ResultsOpenCoder 1.5B Instruct - 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
5480
tokens/s
87.6
tokens/s
200
ms
pp4096+tg256
3714
tokens/s
64.9
tokens/s
1.12
sec
pp2048+tg256
4353
tokens/s
79.1
tokens/s
483
ms
pp2048+tg768
4517
tokens/s
76.4
tokens/s
466
ms
pp1024+tg1024
5591
tokens/s
84.0
tokens/s
195
ms
pp1280+tg3072
5201
tokens/s
73.4
tokens/s
258
ms
pp384+tg1152
6811
tokens/s
89.6
tokens/s
67
ms
pp64+tg1024
3604
tokens/s
93.3
tokens/s
28
ms
pp16+tg1536
1014
tokens/s
90.7
tokens/s
26
ms