Mlx

Explore recommended reads, summarized by AI

MLX Framework and Ecosystem

Analysis of Apple's MLX framework, its performance characteristics, and position in the AI development landscape.

MLX Performance and Integration

Running Models on Apple Silicon

Techniques and tools for deploying and optimizing machine learning models on Mac hardware.

Building Apps with MLX-Swift

Fine-Tuning and Serving LLMs

Quantization and Compression Techniques

Popular this week

Data Science Collective

Ankit Agrawal

5 Ollama and MLX Settings to Optimise for a Local LLM on a Mac in 2026

4d ago

David Fekke

MLX-Serve is the best way to serve AI inference locally on a Mac

Sep 27

Michael Hannecke

ComfyUI + MLX on Apple Silicon: The Clean, Native Setup

Jul 27

Mac O’Clock

Michael Hannecke

mlx-lm vs oMLX: I Was Wrong About the Winner

Jun 23

Sarath S

I deleted LM Studio after a week with omlx

Jul 16

Latest stories

Data Science Collective

Ankit Agrawal

5 Ollama and MLX Settings to Optimise for a Local LLM on a Mac in 2026

4d ago

Salt Index

Rothyyorn

Ollama vs MLX: I Compared Speed, Memory Use, and Setup on Mac

Oct 29

Paul Hackenberger

🕵️ A fast, reliable, offline Community Moderator Agent — Part IV: Kontext is Key

Oct 29

Paul Hackenberger

🕵️ A fast, reliable, offline Community Moderator Agent — Part III: Finetuning

Oct 22

Varun Nuthalapati

Ollama Now Speaks “Decision”: Jev-Style Models Arrive in the CLI, on MLX by Default

Oct 21

See more stories

Mlx

MLX Framework and Ecosystem

MLX Performance and Integration

Running Models on Apple Silicon

Building Apps with MLX-Swift

Fine-Tuning and Serving LLMs

Quantization and Compression Techniques

Popular this week

5 Ollama and MLX Settings to Optimise for a Local LLM on a Mac in 2026

MLX-Serve is the best way to serve AI inference locally on a Mac

ComfyUI + MLX on Apple Silicon: The Clean, Native Setup

mlx-lm vs oMLX: I Was Wrong About the Winner

I deleted LM Studio after a week with omlx

Latest stories

5 Ollama and MLX Settings to Optimise for a Local LLM on a Mac in 2026

Ollama vs MLX: I Compared Speed, Memory Use, and Setup on Mac

🕵️ A fast, reliable, offline Community Moderator Agent — Part IV: Kontext is Key

🕵️ A fast, reliable, offline Community Moderator Agent — Part III: Finetuning

Ollama Now Speaks “Decision”: Jev-Style Models Arrive in the CLI, on MLX by Default

Who to follow

Popular this week

5 Ollama and MLX Settings to Optimise for a Local LLM on a Mac in 2026

MLX-Serve is the best way to serve AI inference locally on a Mac

ComfyUI + MLX on Apple Silicon: The Clean, Native Setup

mlx-lm vs oMLX: I Was Wrong About the Winner

I deleted LM Studio after a week with omlx

Latest stories

5 Ollama and MLX Settings to Optimise for a Local LLM on a Mac in 2026

Ollama vs MLX: I Compared Speed, Memory Use, and Setup on Mac

🕵️ A fast, reliable, offline Community Moderator Agent — Part IV: Kontext is Key

🕵️ A fast, reliable, offline Community Moderator Agent — Part III: Finetuning

Ollama Now Speaks “Decision”: Jev-Style Models Arrive in the CLI, on MLX by Default

Who to follow