TEST #3008 RESULTS
03/07/2026 - 10:07 PM
ACCELERATOR
MODEL
807
tokens/s
generation
19
ms
time to first token
74142
tokens/s
prompt
14542
LocalScore
HOW YOU STACK UP
Explore All ResultsTiny Lm 8M - 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
94259
tokens/s
786
tokens/s
13
ms
pp4096+tg256
55923
tokens/s
686
tokens/s
75
ms
pp2048+tg256
82948
tokens/s
828
tokens/s
26
ms
pp2048+tg768
90165
tokens/s
809
tokens/s
24
ms
pp1024+tg1024
119583
tokens/s
839
tokens/s
10
ms
pp1280+tg3072
108881
tokens/s
782
tokens/s
13
ms
pp384+tg1152
91983
tokens/s
836
tokens/s
5
ms
pp64+tg1024
18151
tokens/s
858
tokens/s
5
ms
pp16+tg1536
5391
tokens/s
843
tokens/s
4
ms