TEST #1614 RESULTS
10/07/2025 - 10:33 PM
ACCELERATOR
MODEL
28.5
tokens/s
generation
1.98
sec
time to first token
766
tokens/s
prompt
223
LocalScore
HOW YOU STACK UP
Explore All Resultstinyllama_tinyllama-1.1b-chat-v1.0 - Q4_K - Medium
SYSTEM
CPU
Intel Core i5-10400 CPU @ 2.90GHz (skylake)
RAM
31.3GB
OS
Linux
Kernel Release
6.8.0-84-generic
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #84-Ubuntu SMP PREEMPT_DYNAMIC Fri Sep 5 22:36:38 UTC 2025
RUNTIME
Name
llamafile
Version
0.9.3
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
827
tokens/s
34.5
tokens/s
1.27
sec
pp4096+tg256
571
tokens/s
10.3
tokens/s
7.27
sec
pp2048+tg256
719
tokens/s
18.9
tokens/s
2.90
sec
pp2048+tg768
715
tokens/s
17.0
tokens/s
2.92
sec
pp1024+tg1024
822
tokens/s
25.5
tokens/s
1.27
sec
pp1280+tg3072
793
tokens/s
14.8
tokens/s
1.65
sec
pp384+tg1152
897
tokens/s
37.3
tokens/s
443
ms
pp64+tg1024
923
tokens/s
54.6
tokens/s
76
ms
pp16+tg1536
625
tokens/s
43.7
tokens/s
31
ms