TEST #2829 RESULTS
02/24/2026 - 4:35 AM
ACCELERATOR
MODEL
200
tokens/s
generation
148
ms
time to first token
10035
tokens/s
prompt
2385
LocalScore
HOW YOU STACK UP
Explore All Resultsh2o-danube3-500m-chat - Q5_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
11780
tokens/s
193
tokens/s
93
ms
pp4096+tg256
7202
tokens/s
179
tokens/s
574
ms
pp2048+tg256
9781
tokens/s
206
tokens/s
214
ms
pp2048+tg768
10290
tokens/s
200
tokens/s
204
ms
pp1024+tg1024
13320
tokens/s
202
tokens/s
83
ms
pp1280+tg3072
12370
tokens/s
193
tokens/s
108
ms
pp384+tg1152
17132
tokens/s
207
tokens/s
27
ms
pp64+tg1024
6071
tokens/s
208
tokens/s
15
ms
pp16+tg1536
2371
tokens/s
209
tokens/s
11
ms