QLoRA fine-tune Gemma 4 E2B with Unsloth as a model router

Melvin Vivas · X post · 2026-09-20 · Open on X

Topics: Fine-tuning & Model Customization, LLMOps, Deployment & Monitoring · Level: intermediate

Summary

The creator QLoRA fine-tuned Gemma 4 E2B Instruct with Unsloth to classify software tasks and send each one to Luna (cheaper) or Astra (stronger). The notebook runs in Google Colab and is shared in his donvito/notebooks repo. He hasn't plugged it into Codex yet and asks others to try.

Key points

• Model routing: a small classifier model decides which larger model should handle each task.
• Base model: Gemma 4 E2B Instruct, small enough to fine-tune cheaply.
• Method: QLoRA (LoRA adapters on a quantized model) with Unsloth.
• Labels: software tasks are routed to luna or astra.
• Runs in Google Colab; the notebook is in github.com/donvito/notebooks.
• Not yet integrated with Codex, so wiring it up is left open.

Resources mentioned

• donvito/notebooks · repo · github.com · free
  The creator's notebooks for fine-tuning and running local models, which you can run in Google Colab, including a GLiNER2.5-Decide intent classification example.
  Also in: Run Local Models on a Free GPU with Google Colab (T4) (Melvin Vivas on X · notes), Free Colab Notebooks for Local Model Fine-Tuning and Inference (Melvin Vivas on X · notes), Intent classification for support using GLiNER2.5-Decide notebook (Melvin Vivas on X · notes), Getting started with GLiNER2.5-Decide in a Colab notebook (Melvin Vivas on X · notes) and 3 more
• 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
• Gemma 4 E2B Instruct · tool · huggingface.co · free
  Small open-weight instruction-tuned Gemma model, used here as the base for a QLoRA fine-tune.
  Also in: Base vs fine-tuned Gemma 4 E2B as a model router (Melvin Vivas on X · notes), Free Colab Notebooks: ModernBERT, Gemma QLoRA, GLiNER & Guardrails (Melvin Vivas on X · notes)
• Google Colab · tool · colab.research.google.com · free · recommended by both Bashiri Smith & Melvin Vivas
  Free GPU notebooks.
  Also in: Run Notebooks on a Free GPU with Google Colab (T4, 15GB VRAM) (Melvin Vivas on X · notes), Run Local Models on a Free GPU with Google Colab (T4) (Melvin Vivas on X · notes), Free Colab Notebooks for Local Model Fine-Tuning and Inference (Melvin Vivas on X · notes), Intent classification for support using GLiNER2.5-Decide notebook (Melvin Vivas on X · notes) and 12 more
• OpenAI Codex · tool · openai.com · paid
  OpenAI's coding agent. In the diagram it writes code, fixes review findings and drives the build loop. The creator also used it to make this video.
  Also in: An agent bot that installs and drives Codex on its own (Melvin Vivas on X · notes), Asking a Coder bot to install Codex (Melvin Vivas on X · notes), Sign in with ChatGPT: Setting Usage Limits for Each App (Melvin Vivas on X · notes), Codex Cloud Environments Must Be Saved & Published Before Use (Melvin Vivas on X · notes) and 240 more

Try this

• Open the Colab notebook in donvito/notebooks and run the QLoRA fine-tune.
• Try wiring the router into Codex and share the results with the creator.
• Build a cost-saving model router: a fine-tuned small model that sends each coding task to a cheap or a strong model, connected to Codex.