Unlimited Free AI Coding with Unsloth's Qwen 3.5 on an RTX 3090

Melvin Vivas · X post · 2026-03-08 · Open on X

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

Summary

The creator does unlimited, free AI coding with Unsloth's build of Qwen 3.5 running on one RTX 3090. It shows that local coding models are practical on consumer GPUs.

Key points

• Unsloth publishes quantized builds of Qwen 3.5 that run on consumer GPUs.
• One RTX 3090 (24 GB) is enough for local AI coding.
• Running locally means no usage limits or API bills.

Resources mentioned

• Unsloth · tool · unsloth.ai · free
  Open-source library for fast, memory-efficient fine-tuning of open LLMs (LoRA/QLoRA) on a single GPU or in Colab.
  Also in: Run Laya Decision models locally with Unsloth on 4GB RAM (Melvin Vivas on X · notes), Unsloth passes 500M model downloads on Hugging Face (Melvin Vivas on X · notes), Run Qwen-Image-2.1 locally on 12GB VRAM with Unsloth GGUFs (Melvin Vivas on X · notes), Base vs fine-tuned Gemma 4 E2B as a model router (Melvin Vivas on X · notes) and 29 more
• Qwen 3.5 · tool · qwen.ai · free
  Alibaba Qwen open model family with small on-device variants and toggleable reasoning.
  Also in: Workshop AI: Building Apps with Cloud and Local Agents (GLM 5, Qwen 3.5) (Melvin Vivas on X · notes), Qwen3.5 0.8B Does Real-Time Local Video Captioning (Melvin Vivas on X · notes), Qwen3.5 0.8B Real-Time Video Captioning on Mac Studio (Melvin Vivas on X · notes), Qwen 3.5 Is the Local Model That Holds Up in Claude Code (Melvin Vivas on X · notes) and 7 more