TEST #2236 RESULTS
01/11/2026 - 5:07 AM
ACCELERATOR
MODEL
16.6
tokens/s
generation
27.38
sec
time to first token
51
tokens/s
prompt
31
LocalScore
HOW YOU STACK UP
Explore All ResultsDeepseek Coder 1.3b Instruct - Q4_K - Medium
SYSTEM
CPU
12th Gen Intel Core i3-1215U (alderlake)
RAM
11.7GB
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
54
tokens/s
19.2
tokens/s
19.18
sec
pp4096+tg256
45
tokens/s
10.8
tokens/s
91.94
sec
pp2048+tg256
50
tokens/s
15.7
tokens/s
41.32
sec
pp2048+tg768
50
tokens/s
14.7
tokens/s
40.87
sec
pp1024+tg1024
53
tokens/s
17.1
tokens/s
19.30
sec
pp1280+tg3072
51
tokens/s
13.5
tokens/s
25.12
sec
pp384+tg1152
54
tokens/s
19.0
tokens/s
7.10
sec
pp64+tg1024
52
tokens/s
20.4
tokens/s
1.27
sec
pp16+tg1536
53
tokens/s
19.5
tokens/s
346
ms