Free Colab Notebooks: LFM2.5 2.6B Tool Calling and Benchmarks
Melvin Vivas · X post · 2026-08-19 · Open on X
Topics: AI Agents, Tool Use & MCP, LLM Fundamentals · Level: beginner
Summary
The creator added a Notebooks section to his website for free Colab notebooks. The first one runs LFM2.5 2.6B with a tool-call example and some quick benchmarks.
Key points
- Free Colab notebooks are listed at donvitocodes.com/notebooks.
- The first notebook covers LFM2.5 2.6B, a small model.
- It includes a tool-calling example and quick benchmarks.
Resources mentioned
- Colab Notebooks | DonvitoCodes · website · donvitocodes.com · free
The creator's collection of Colab notebooks for running local models, starting with chat and tool calling on LFM2.5-2.6B.
Also in: Free Colab Notebooks: ModernBERT, Gemma QLoRA, GLiNER & Guardrails (Melvin Vivas on X · notes), DonvitoCodes Colab notebooks for running local models (LFM2.5-2.6B) (Melvin Vivas on X · notes) - LFM2.5-2.6B · tool · huggingface.co · free
Liquid AI's small language model, which can be paired with the LFM2.5-VL-3B vision model.
Also in: Coworker: Open-Source Work Agent That Runs on Small Local Models (Melvin Vivas on X · notes), Coworker with Liquid AI LFM2.5-2.6B via LM Studio on a Mac (Melvin Vivas on X · notes), Zero-Cost Coworker Setup: OpenRouter Free Models + Local LFM2.5 (Melvin Vivas on X · notes), Coworker: A Subscription-Free AI Agent on Local LFM2.5-2.6B (Melvin Vivas on X · notes) and 9 more - 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
Try this
- Open the LFM2.5 2.6B notebook and run the tool-call example.
- Benchmark a small open model's tool calling in a Colab notebook.
More in AI Agents, Tool Use & MCP
- Mixture-of-Agents Setting Was Quietly Using Up Codex/ChatGPT Quota
- Mind Viruses: How Bad Ideas Spread Through Multi-Agent LLM Systems
- Running DeepSeek V4 Pro on Baseten with the Pi Agent Harness
- DeepSeek harness: open-source agent with an inspectable trajectory view
- Agent Loops in ML Engineering: Liquid AI's Vibe-Coded Tokenizer Trainer
- Comfy MCP Goes Local and Open-Source: Agents That See Your Install