TEST #2832 RESULTS
02/24/2026 - 4:38 AM
ACCELERATOR
MODEL
173
tokens/s
generation
147
ms
time to first token
9982
tokens/s
prompt
2276
LocalScore
HOW YOU STACK UP
Explore All Resultsh2o-danube3-500m-chat - Q8_0
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
12965
tokens/s
169
tokens/s
85
ms
pp4096+tg256
7256
tokens/s
159
tokens/s
570
ms
pp2048+tg256
9859
tokens/s
177
tokens/s
213
ms
pp2048+tg768
10666
tokens/s
172
tokens/s
198
ms
pp1024+tg1024
12592
tokens/s
175
tokens/s
87
ms
pp1280+tg3072
12807
tokens/s
168
tokens/s
105
ms
pp384+tg1152
15600
tokens/s
180
tokens/s
30
ms
pp64+tg1024
6181
tokens/s
180
tokens/s
20
ms
pp16+tg1536
1915
tokens/s
180
tokens/s
13
ms