TEST #2511 RESULTS
02/01/2026 - 11:39 PM
ACCELERATOR
MODEL
166
tokens/s
generation
60
ms
time to first token
23516
tokens/s
prompt
4032
LocalScore
HOW YOU STACK UP
Explore All ResultsFunctiongemma-270M-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
30531
tokens/s
140
tokens/s
41
ms
pp4096+tg256
19862
tokens/s
157
tokens/s
212
ms
pp2048+tg256
29262
tokens/s
170
tokens/s
76
ms
pp2048+tg768
29376
tokens/s
174
tokens/s
77
ms
pp1024+tg1024
34144
tokens/s
172
tokens/s
35
ms
pp1280+tg3072
30383
tokens/s
168
tokens/s
48
ms
pp384+tg1152
29017
tokens/s
172
tokens/s
18
ms
pp64+tg1024
7035
tokens/s
171
tokens/s
15
ms
pp16+tg1536
2037
tokens/s
174
tokens/s
13
ms