RepoRadar
Leave a Tip
Item detail

Blaizzy/mlx-vlm

Blaizzy mlx-vlm is an MIT open-source Python package for inference and fine-tuning of Vision-Language Models (VLMs) on Apple Silicon using Apple's MLX framework, with first-class support for Qwen2-VL, Qwen2.5-VL, LLaVA, Idefics, Pixtral, Phi-3.5-Vision, SmolVLM, Molmo, and other modern VLMs, so a developer with a Mac (M1/M2/M3/M4) can run multimodal inference locally with unified-memory speed and

Open source →Back to radar
Score7.4
Popularity5080.0
Risklow
TierGold
Score breakdown
Usefulness7.8
Novelty10.0
Momentum10.0
Maturity8.4
Open-source/build7.4
Evidence7.2
Workflow potential8.1
Setup ease6.5

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for local AI users, Mac developers, and researchers who want to run or fine-tune Vision-Language Models (Qwen2-VL, LLaVA, Pixtral, SmolVLM, Phi-3.5-Vision, Molmo, Idefics) locally on Apple Silicon using the MLX framework, because Blaizzy mlx-vlm ships inference and fine-tuning for the major open VLMs in a single MIT-licensed Python package, which means a developer with a Mac (M1/M2/M3/M4) c

Who should use it

BuildersPower users

Who should skip it

Skip if the source link, docs, or setup requirements do not match your workflow.

Risk explanation

Risk label needs manual review.

Evidence links

Closest alternatives / related signals