TEST #1597 RESULTS
10/06/2025 - 11:48 PM
ACCELERATOR
MODEL
10.0
tokens/s
generation
10.58
sec
time to first token
133
tokens/s
prompt
50
LocalScore
HOW YOU STACK UP
Explore All ResultsMeta Llama 3.1 8B Instruct - 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
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
139
tokens/s
12.1
tokens/s
7.44
sec
pp4096+tg256
116
tokens/s
4.0
tokens/s
35.58
sec
pp2048+tg256
129
tokens/s
7.0
tokens/s
15.95
sec
pp2048+tg768
129
tokens/s
6.4
tokens/s
15.95
sec
pp1024+tg1024
138
tokens/s
9.3
tokens/s
7.50
sec
pp1280+tg3072
136
tokens/s
5.6
tokens/s
9.50
sec
pp384+tg1152
144
tokens/s
13.0
tokens/s
2.71
sec
pp64+tg1024
145
tokens/s
17.8
tokens/s
470
ms
pp16+tg1536
116
tokens/s
14.8
tokens/s
163
ms