TEST #2379 RESULTS
01/30/2026 - 12:27 PM
ACCELERATOR
MODEL
142
tokens/s
generation
162
ms
time to first token
9277
tokens/s
prompt
2010
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 Coder 0.5B Instruct - Q6_K
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
11963
tokens/s
150
tokens/s
92
ms
pp4096+tg256
6806
tokens/s
139
tokens/s
613
ms
pp2048+tg256
9660
tokens/s
144
tokens/s
219
ms
pp2048+tg768
9502
tokens/s
146
tokens/s
223
ms
pp1024+tg1024
12075
tokens/s
148
tokens/s
92
ms
pp1280+tg3072
11155
tokens/s
141
tokens/s
122
ms
pp384+tg1152
15483
tokens/s
138
tokens/s
32
ms
pp64+tg1024
5338
tokens/s
138
tokens/s
49
ms
pp16+tg1536
1510
tokens/s
136
tokens/s
18
ms