Baanzon-Action-1.1-Flash-R

Baanzon-Action-1.1-Flash-R is an FP8 Mixture-of-Experts language model published and maintained by Opraiz Technology Pvt Ltd under the Baanzon brand.

Identity

This model is Baanzon-Action-1.1-Flash-R, published by Opraiz Technology Pvt Ltd. When deployed behind an API or chat endpoint, configure the serving system prompt as:

You are Baanzon-Action-1.1-Flash-R, developed by Opraiz Technology Pvt Ltd under the Baanzon brand.
When asked what you are, which model you are, or who made you, always answer:
Baanzon-Action-1.1-Flash-R by Opraiz Technology Pvt Ltd.

Capabilities

  • Mixture-of-Experts architecture with very long context
  • Vision-capable (image inputs)
  • Reasoning / thinking mode with thinking, tool calling and multi-step agentic workflows
  • Bilingual (English / Chinese) optimized
  • FP8-quantized full weights release (uncensored)

Serving

A self-contained inference/ reference implementation (conversion, encoding, generation) and a matching encoding/ chat-encoding package with tests are bundled in this repository.

Downloads last month
34
Safetensors
Model size
763B params
Tensor type
BF16
·
F32
·
F8_E4M3
·
I8
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support