Running MiniMax M3 Locally in ComfyUI on an RTX 3090

Melvin Vivas · X post · 2026-08-07 · Open on X

Topics: AI Dev Tools & Productivity · Level: intermediate

Summary

The creator got MiniMax's M3 model running locally in ComfyUI on a consumer RTX 3090 GPU. He expects generation to be slow ("a long night"). This shows that the model can run on local hardware, but slowly on a 24GB consumer card.

Key points

• MiniMax M3 can run locally through ComfyUI.
• On a single RTX 3090 (24GB), the creator expects generation to be slow.
• Plan for long run times when running large generative models on consumer GPUs.

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), Demo: Real-Time VFX Compositing Inside ComfyUI (Melvin Vivas on X · notes) and 23 more
• MiniMax (official) · person · x.com · free
  MiniMax's official X account; MiniMax is the AI lab behind the M3 and H3 models.
  Also in: MiniMax 2.7 One-Shots a Linear Clone at 95% Lower Cost (Melvin Vivas on X · notes)