Category: Gemini

Guide: Run Gemma 4 NVFP4 From ComfyUI

Published by Zanno on 19 April 2026

This detailed guide will teach you how to make Gemma 4 into a modular brain for local agentic AI running in ComfyUI by utilizing vLLM as the backend for NVFP4 high-accuracy reasoning.

Complete Your Local Gemma 4 With RAG Memory

Complete Your Local Gemma 4 With RAG Memory

Published by Zanno on 11 April 2026

Setup you local agentic AI. Learn how to integrate a private RAG memory with Gemma 4 using OpenClaw and LanceDB. This guide solves the ‘Unsupported model’ and dimension mismatch errors for a truly autonomous local partner.

Local OpenClaw With Gemma 4 GGUF

Local OpenClaw With Gemma 4 GGUF

Published by Zanno on 10 April 2026

Tired of NVFP4 compatibility issues? Run the new Gemma 4 E4B as local agentic AI. From llama.cpp installation to OpenClaw integration, get the definitive local AI setup.”

Banned From Patreon

Banned From Patreon

Published by Zanno on 28 March 2026

If I shared techniques for analogue photography, those could be used by someone to produce NSFW photography.

MXFP8 vs NVFP4: Finding the Blackwell Sweet Spot

MXFP8 vs NVFP4: Finding the Blackwell Sweet Spot

Published by Zanno on 25 March 2026

Is MXFP8 better than NVFP4? I benchmarked both on NVIDIA Blackwell to find the sweet spot between 7.62s render speeds and high-fidelity quality. See the truth.