Elsephire

Qwen3.5-0.8B-Holo-3.1-0.8B-80-20-Beta

README

License: mit

About this model

This model was created by merging Qwen3.5-0.8B and Holo-3.1-0.8B using Task Arithmetic with an 80/20 weighting ratio. The merge was performed using Minerve-Fusion, a tool that will be released open-source in the near future.

⚠️ This is a beta release. Testing and feedback are highly encouraged!

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Model Details

Model Provider

Elsephire

Model Tree

Base

Hcompany/Holo-3.1-0.8B

Base

Qwen/Qwen3.5-0.8B

Merged

this model

Input Modalities

TextImageVideo

Output Modalities

Text

Supported Functionality

Dedicated Endpoints

Explore FriendliAI today

Get started Talk to an engineer

Qwen3.5-0.8B-Holo-3.1-0.8B-80-20-Beta API & Inference Endpoint | FriendliAI