TEST #2819 RESULTS
02/24/2026 - 4:27 AM
ACCELERATOR
MODEL
210
tokens/s
generation
162
ms
time to first token
8760
tokens/s
prompt
2246
LocalScore
HOW YOU STACK UP
Explore All Resultsh2o-danube3-500m-chat - Q2_K - Small
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
10534
tokens/s
176
tokens/s
102
ms
pp4096+tg256
6684
tokens/s
193
tokens/s
618
ms
pp2048+tg256
9173
tokens/s
218
tokens/s
228
ms
pp2048+tg768
9180
tokens/s
214
tokens/s
228
ms
pp1024+tg1024
10538
tokens/s
218
tokens/s
101
ms
pp1280+tg3072
10562
tokens/s
210
tokens/s
126
ms
pp384+tg1152
14360
tokens/s
222
tokens/s
30
ms
pp64+tg1024
5442
tokens/s
219
tokens/s
16
ms
pp16+tg1536
2367
tokens/s
222
tokens/s
13
ms