202 2 weeks ago

Ling-3.0-tiny, a lightweight hybrid reasoning MoE model with 7.9B total parameters and only 1.3B activated parameters per token. It is designed to deliver strong reasoning and agentic capabilities at low inference cost, making advanced model capabilities.

thinking
ollama run AntLing/Ling-3.0-tiny:q8_0

Details

2 weeks ago

1396e4a35341 · 8.4GB ·

bailingmoe3
·
7.89B
·
Q8_0
{{- if .System }}<role>SYSTEM</role>{{ .System }} {{- if .Think }} detailed thinking on{{ else }} de
{ "stop": [ "<|role_end|>", "<|endoftext|>" ], "temperature": 1, "to

Readme

No readme