TEST #2376 RESULTS
01/30/2026 - 12:19 PM
ACCELERATOR
MODEL
98.1
tokens/s
generation
160
ms
time to first token
8031
tokens/s
prompt
1700
LocalScore
HOW YOU STACK UP
Explore All ResultsGemma-3-1B-It - 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
10211
tokens/s
93.8
tokens/s
112
ms
pp4096+tg256
8032
tokens/s
92.4
tokens/s
521
ms
pp2048+tg256
9392
tokens/s
96.8
tokens/s
228
ms
pp2048+tg768
9235
tokens/s
98.9
tokens/s
233
ms
pp1024+tg1024
10518
tokens/s
101
tokens/s
108
ms
pp1280+tg3072
9559
tokens/s
99.8
tokens/s
144
ms
pp384+tg1152
10144
tokens/s
102
tokens/s
47
ms
pp64+tg1024
4074
tokens/s
99.7
tokens/s
25
ms
pp16+tg1536
1113
tokens/s
98.2
tokens/s
24
ms