Skip to main content
← Back to news

funcroute: a router that gives a text-only LLM model eyes and ears

Use cases
Source:Hacker News
A small open-source router (v0.4.0) that adds multimodal capabilities to a text-only LLM model: images and audio are handled at the routing layer, so the local model stays the one you already run, without swapping it out.
Read original article

Related articles

Decision models in local: JEV-35B and the 3B-active System 1

You don't need a big LLM to decide. JEV-35B (35B, 3B active) in NVFP4 on a 32GB GPU and ej (11.4MB) on CPU show how to do routing, classification and quality control without generating a single token.

Qwen-Image 2.1: Generate and Edit Images Locally

Qwen's 7B open model that generates, edits, and creates transparent images: how to run it locally with diffusers and ComfyUI.

Llama 3 and Llama 4: Meta's open family — which model runs on your hardware

From the 3.1 8B to the 4 Scout MoE with a 10M context: the Llama family in a table, what runs on 16, 48 and 128 GB of RAM, the Community license translated for the Italian business and the choice by budget.

Get the next local-AI briefing

Once a week, the top selection from iaLocale: articles, news and resources on local AI, and more.

After signing up you receive a confirmation email (double opt-in). Without confirmation we send nothing. No spam, we promise.

Related resources

Tools and resources from the iaLocale archive relevant to this content.

🎨

Qwen-Image 2.1

Models

7B open-weight model (32-layer DiT) that unifies text-to-image generation up to 2048x2048, editing with up to 10 reference images, and native RGBA transparency. Designed to run locally on 16GB+ VRAM; supported by diffusers and ComfyUI.

⚡

faster-whisper

Inference

Reimplementation of Whisper based on CTranslate2: up to 4 times faster than openai/whisper with the same accuracy and less memory. Supports 8-bit quantization on both CPU and GPU.

🎵

Kokoro-82M

Models

82-million-parameter speech synthesis model on a VITS architecture, Apache-2.0 for the weights, with voices in dozens of languages and surprisingly high quality for its size. Runs efficiently on CPU alone.

🤖

OpenAI gpt-oss-20b

Models

Il modello di ragionamento open-weight di OpenAI: MoE con 21B di parametri totali e 3,6B attivi (32 esperti, top-4), contesto 128K e quantizzazione MXFP4 nativa. Licenza Apache 2.0: i pesi partono già quantizzati a 4 bit, senza passo di conversione. Sta in 16GB di VRAM e gira anche su RAM unificata o CPU.

Browse all resources