Fine-tune and Run Local Models for Free on Google Colab's T4 GPU
Melvin Vivas · X video post · 2026-10-08 · 0:17 · 365 views · Open on X
Topics: Fine-tuning & Model Customization, LLMOps, Deployment & Monitoring · Level: beginner
Summary
Melvin Vivas shares a GitHub collection of notebooks for fine-tuning local (open-weight) models and running inference on them. All of the notebooks run on the free T4 GPU in Google Colab, so you don't have to buy a GPU. The video explains how to get started: open Colab, sign in with a Google account, and run any notebook on the free GPU, which has about 15 GB of VRAM.
Key points
- You don't need to buy a GPU to experiment with fine-tuning and inference on local models.
- Go to colab.research.google.com (Google Colab) and sign in with your Gmail/Google account.
- Colab's free tier gives you an NVIDIA T4 GPU with about 15 GB of VRAM.
- You can run any notebook you find in Colab on that free GPU.
- The creator's notebooks repo (github.com/donvito/...) covers both fine-tuning and inference, and every notebook is made to fit the free T4.
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 LightOnOCR-3 0.8B and Other Open Models on a Free Colab T4 (Melvin Vivas on X · notes), Try Liquid AI's open d1-3B decision model in Colab (Melvin Vivas on X · notes), Try EmbeddingGemma 2 multimodal embeddings in Colab (Melvin Vivas on X · notes), Colab Notebook for Liquid AI's d1-3B Decision Model (Melvin Vivas on X · notes) and 10 more - Google Colab · tool · colab.research.google.com · free · recommended by both Bashiri Smith & Melvin Vivas
Free GPU notebooks.
Also in: Run LightOnOCR-3 0.8B and Other Open Models on a Free Colab T4 (Melvin Vivas on X · notes), Try Liquid AI's open d1-3B decision model in Colab (Melvin Vivas on X · notes), Google Colab notebooks for new open models, built by a coding agent (Melvin Vivas on X · notes), Liquid AI's LFM2.5-24B-A2B: a local MoE model for agent tasks (Melvin Vivas on X · notes) and 27 more - NVIDIA T4 GPU · tool · nvidia.com · free
The GPU that comes with Colab's free tier, with about 15 GB of VRAM. It's enough for small-model fine-tuning and inference.
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)
Try this
- Open colab.research.google.com and sign in with your Google/Gmail account.
- Set the Colab runtime to the free T4 GPU.
- Find the creator's notebooks repo on GitHub (donvito). The caption link is cut off. Then open a fine-tuning or inference notebook in Colab and run it.
- Fine-tune a small local model with one of the notebooks on Colab's free T4, then run inference with the result.
More in Fine-tuning & Model Customization
- Fine-tuned Qwen3.5-9B beat frontier models for Coinbase fraud task
- A100 80GB GPUs in Google Colab via Google AI Pro plans
- The Open Env Arena: Agents Design RL Environments, Ranked on a Leaderboard
- Free Colab notebooks for fine-tuning and running local models
- Agent tasks: Unsloth fine-tuning, ComfyUI face swap, script writing
- Train Your Own Decision Model Locally with Unsloth