TEST #1613 RESULTS
10/07/2025 - 10:21 PM
ACCELERATOR
MODEL
71.4
tokens/s
generation
919
ms
time to first token
1509
tokens/s
prompt
489
LocalScore
HOW YOU STACK UP
Explore All Resultstinyllama_tinyllama-1.1b-chat-v1.0 - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-7400 CPU @ 3.00GHz (skylake)
RAM
15.6GB
OS
Linux
Kernel Release
6.8.0-85-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #85-Ubuntu SMP PREEMPT_DYNAMIC Thu Sep 18 15:26:59 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1780
tokens/s
81.1
tokens/s
588
ms
pp4096+tg256
1248
tokens/s
43.0
tokens/s
3.31
sec
pp2048+tg256
1538
tokens/s
63.9
tokens/s
1.35
sec
pp2048+tg768
1536
tokens/s
60.1
tokens/s
1.35
sec
pp1024+tg1024
1752
tokens/s
73.9
tokens/s
596
ms
pp1280+tg3072
1651
tokens/s
54.7
tokens/s
788
ms
pp384+tg1152
1870
tokens/s
84.6
tokens/s
215
ms
pp64+tg1024
1521
tokens/s
94.0
tokens/s
51
ms
pp16+tg1536
683
tokens/s
87.4
tokens/s
32
ms