t-firefly/qwen3.5-0.8b-rknn3-rk1828

<div align="center"> <img src="./firefly-logo-outline.png" width="150" alt="Firefly">

<h1>Qwen3.5-0.8B</h1>

<p> <code>RK1828</code> &nbsp; | &nbsp; <code>LlamaPi Ready</code> </p> </div>

Model Overview

Run with LlamaPi

llamapi run qwen3.5:0.8b

llamapi run handles model download, loading, and execution. See the LlamaPi Wiki for setup and usage.

About the Original Model

Qwen3.5-0.8B is a compact native vision-language model from the Qwen3.5 family, well suited for prototyping, task-specific fine-tuning, and research.

• —Unifies vision and language understanding through early-fusion multimodal training.
• —Built on an efficient hybrid architecture (Gated Delta Networks with sparse Mixture-of-Experts) for high-throughput, low-latency inference.
• —Supports 201 languages and dialects with a native 262,144-token context window.

License & Attribution

The models provided in this repository are converted and adapted by the Firefly AI team from the original models. All intellectual property rights and copyright in the underlying original models remain with the original official team, and their distribution is governed by the corresponding official open-source license.