# mlx-vlm

5 Hacker News commenters recommended mlx-vlm and 2 criticized it, November 2025 to November 2026. It was recommended in 3 of 13 months.

**Verdict:** Runs vision-language models on Apple silicon with MLX and is said to infer faster than llama.cpp on Apple devices. Critics report bugs and weak support for modern samplers.

## Why people recommend it

- Faster inference on Apple devices (1 comments): "it can provide faster inference on Apple devices than llama.cpp" ([source](https://news.ycombinator.com/item?id=48984710))
- Supports min-p sampling (1 comments): "TBF mlx-vlm does support min-p sampling, but none of the other modern samplers that you list." ([source](https://news.ycombinator.com/item?id=48991935))
- Recently updated by maintainer (1 comments): "Prince Canuma just updated mlx-vlm" ([source](https://news.ycombinator.com/item?id=47622378))

## What people warn about

- Weak support for modern samplers (2 comments): "Switching to mlx-vlm is basically harmful since it (like vllm and sglang) have such garbage support for modern samplers." ([source](https://news.ycombinator.com/item?id=48990705)) "TBF mlx-vlm does support min-p sampling, but none of the other modern samplers that you list." ([source](https://news.ycombinator.com/item?id=48991935))
- Many bugs, not official (1 comments): "that is not official and has tons of bugs" ([source](https://news.ycombinator.com/item?id=47301792))

## Alternatives hackers recommend

- [vLLM](https://hackerapproved.com/p/vllm.md): 112 recommend
- [Strata](https://hackerapproved.com/p/strata.md): 31 recommend
- [DwarfStar 4](https://hackerapproved.com/p/dwarfstar.md): 26 recommend
- [SGLang](https://hackerapproved.com/p/sglang.md): 19 recommend
- [ninfer](https://hackerapproved.com/p/ninfer.md): 16 recommend

## Cite as

Hacker Approved, "mlx-vlm", https://hackerapproved.com/p/mlx-vlm/ (counts from 1,795,640 Hacker News comments, November 2025 to November 2026).