Local Text-Only Workflows in ComfyUI with LM Studio and Gemma 4 E2B

Melvin Vivas · X post · 2026-05-20 · Open on X

Topics: AI Dev Tools & Productivity, LLM Fundamentals · Level: intermediate

Summary

The creator built custom ComfyUI nodes that call Gemma 4 E2B served locally by LM Studio. He uses them for text-only workflows, which shows ComfyUI's node graph can chain local LLMs as well as generate images.

Key points

• ComfyUI custom nodes can call a local LLM server such as LM Studio
• Gemma 4 E2B is a small model that can run locally for text tasks
• ComfyUI's node graph can be used for text-only LLM pipelines, not just image generation
• Everything runs locally, with no API costs

Resources mentioned

• ComfyUI · tool · x.com · free
  The official X account for ComfyUI, the node-based tool for generative AI workflows, which announces things like ComfyUI Agent.
  Also in: ComfyUI Agent: early access announcement (Melvin Vivas on X · notes), Comfy Router: One API for Image, Video, 3D and Audio Model Providers (Melvin Vivas on X · notes), Generating AI Video Locally with MiniMax H3 in ComfyUI on an RTX 3090 (Melvin Vivas on X · notes), Running MiniMax M3 Locally in ComfyUI on an RTX 3090 (Melvin Vivas on X · notes) and 23 more
• LM Studio · tool · x.com · free
  Desktop app for downloading and running LLMs locally, with a developer mode that serves models through an API.
  Also in: Running LLMs Locally Without an Expensive Rig (Melvin Vivas on X · notes), Adding Vercel AI Gateway as a provider in AIBackends with Devin (Melvin Vivas on X · notes), LoRA Fine-Tune Qwen3.5-2B on Your Tweets with Unsloth Studio (Melvin Vivas on X · notes), AIBackends: An API Layer Between Your App and AI Models (Now with Jev) (Melvin Vivas on X · notes) and 31 more
• Gemma 4 · tool · ai.google.dev · free
  Google's family of open-weight models in several sizes, built to run on devices and offline, with multimodal and agentic abilities, and open to fine-tuning.
  Also in: Gemma 4 Runs Locally On-Device in the Antigravity SDK (Melvin Vivas on X · notes), On-Device AI: Running Gemma 4 E2B Offline on an iPhone with LiteRT (Melvin Vivas on X · notes), Running Gemma 4 Models Offline on an iPhone (Melvin Vivas on X · notes), Fine-tuning Gemma4-E2B on your own tweet style with Unsloth (Melvin Vivas on X · notes) and 25 more

Try this

• Build custom ComfyUI nodes that call a local LM Studio model for text-only workflows