TEST #2447 RESULTS
02/01/2026 - 5:49 AM
ACCELERATOR
MODEL
849
tokens/s
generation
10
ms
time to first token
129655
tokens/s
prompt
22030
LocalScore
HOW YOU STACK UP
Explore All ResultsTiny Gemma Test - Q4_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
73529
tokens/s
675
tokens/s
15
ms
pp4096+tg256
157035
tokens/s
773
tokens/s
28
ms
pp2048+tg256
214533
tokens/s
896
tokens/s
11
ms
pp2048+tg768
198177
tokens/s
868
tokens/s
11
ms
pp1024+tg1024
169607
tokens/s
889
tokens/s
8
ms
pp1280+tg3072
190541
tokens/s
868
tokens/s
8
ms
pp384+tg1152
136243
tokens/s
898
tokens/s
4
ms
pp64+tg1024
20805
tokens/s
890
tokens/s
4
ms
pp16+tg1536
6427
tokens/s
884
tokens/s
4
ms