TEST #852 RESULTS
05/10/2025 - 4:14 PM
MODEL
2.1
tokens/s
generation
269.94
sec
time to first token
5
tokens/s
prompt
3
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 Coder 3B Instruct - Q4_K - Medium
SYSTEM
CPU
RAM
15.6GB
OS
Linux
Kernel Release
6.1.43-rockchip-rk3588
Architecture
aarch64
Version
Cosmopolitan 3.9.7 MODE=aarch64; #1.1.8 SMP Fri Feb 2 21:16:10 CST 2024
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
6
tokens/s
1.9
tokens/s
181.75
sec
pp4096+tg256
5
tokens/s
2.0
tokens/s
878.90
sec
pp2048+tg256
4
tokens/s
2.1
tokens/s
482.74
sec
pp2048+tg768
5
tokens/s
2.1
tokens/s
374.70
sec
pp1024+tg1024
5
tokens/s
2.2
tokens/s
188.89
sec
pp1280+tg3072
5
tokens/s
2.1
tokens/s
236.49
sec
pp384+tg1152
5
tokens/s
2.2
tokens/s
71.40
sec
pp64+tg1024
6
tokens/s
2.2
tokens/s
11.01
sec
pp16+tg1536
5
tokens/s
2.2
tokens/s
3.58
sec