OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Models

Labllm

Labllm is an open-source Swift application for macOS that lets users design, train and fine-tune small language models locally on Apple Silicon using MLX.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Labllm — OpenViST project profile in AI Models.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Labllm when you want a local, visual workflow for learning about or experimenting with small language-model training, from model setup and data selection through checkpoints and sampling.

Who it is for

  • Learners exploring model architecture, tokenization and training.
  • Researchers and developers experimenting with small models and custom datasets on an Apple Silicon Mac.

Documented uses

  • Create GPT-style decoder models from presets and adjust model settings.
  • Import or browse datasets and configure training data.
  • Pretrain or fine-tune models using supervised fine-tuning, LoRA or DPO.
  • Monitor training metrics and samples, then save, resume and compare checkpoints.
  • Inspect tokens and embeddings, sample from a model, or chat with a trained model.
Before you choose

Requirements & limits

Labllm is described as free, open source under the MIT license, and available as a native macOS app. The repository documents macOS 14 or later and Apple Silicon M1 or newer as requirements, and labels the software beta.

  • Requires an Apple Silicon Mac running macOS 14 or later; the project documents no Intel Mac path.
  • MLX provides the documented Apple Silicon acceleration, and the first MLX build may take time.
  • The app is in beta, so its feature set and behavior may change.
  • Source builds use Swift Package Manager; Xcode 15 or later is recommended.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Build and launch Labllm from source

Compile and open the native macOS app using the documented Swift Package Manager commands.

Before you start

  • macOS 14 or later
  • Apple Silicon Mac, M1 or newer
  • Swift Package Manager
  • Xcode 15 or later is recommended
  • Time for the first MLX build to complete

Steps

  1. Open the Labllm repository in a terminal.

  2. Run swift build.

  3. Run swift run LabLLM to launch the app.

Expected outcome

The repository is built and the Labllm macOS app is launched.

Guide limitations

  • The project describes this build as beta software and notes that bugs, missing features and fast-moving updates should be expected.
  • Full Xcode is recommended if rebuilding MLX itself.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
Greninja9257/LabLLM · Official homepage title · retained in its source language
How we review sourcesSuggest a correction