TEST #2836 RESULTS
02/24/2026 - 4:41 AM
ACCELERATOR
MODEL
187
tokens/s
generation
121
ms
time to first token
12828
tokens/s
prompt
2709
LocalScore
HOW YOU STACK UP
Explore All ResultsOpenELM 270M - 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
16544
tokens/s
188
tokens/s
66
ms
pp4096+tg256
8472
tokens/s
175
tokens/s
488
ms
pp2048+tg256
12611
tokens/s
190
tokens/s
167
ms
pp2048+tg768
12618
tokens/s
187
tokens/s
167
ms
pp1024+tg1024
17360
tokens/s
188
tokens/s
63
ms
pp1280+tg3072
15860
tokens/s
187
tokens/s
85
ms
pp384+tg1152
22955
tokens/s
189
tokens/s
22
ms
pp64+tg1024
6740
tokens/s
181
tokens/s
14
ms
pp16+tg1536
2287
tokens/s
196
tokens/s
13
ms