MLX-GUI v1.2.4 Private AI API for Apple Silicon (Chat,Audio,Embeddings,Vision)

#1

Post by RamboRogers » Wed, Jul 23, 2025, 6:39 PM UTC

MLX-GUI v1.2.4 Private AI API for Apple Silicon (Chat,Audio,Embeddings,Vision)
mlxgui.com

Re: MLX-GUI v1.2.4 Private AI API for Apple Silicon (Chat,Audio,Embeddings,Vision)

#2

Post by RamboRogers » Wed, Jul 23, 2025, 6:39 PM UTC

Hey HN! I've been building MLX-GUI as an open-source inference server that turns any Mac into a multi-user AI server. v1.2.4 just shipped with some major additions:

Complete Whisper ecosystem (99+ languages, word timestamps, any audio format) 23 embedding models across 13 families (E5, ModernBERT, Arctic, etc.) Mistral Small 24B with vision capabilities OpenAI-compatible API that's actually faster than Ollama on Apple Silicon

The goal was simple: I wanted to use my Mac Mini/Studio as proper inference servers without the complexity of managing Python environments or paying for cloud APIs while keeping data local. It's packaged as a native macOS app (no Python install needed) with a beautiful web GUI for model management. The API is drop-in compatible with OpenAI, so existing apps like Jan.ai work immediately. 900+ lines of tests ensure production reliability. G

NU GPL v3 licensed and actively maintained. GitHub: https://github.com/RamboRogers/mlx-gui

Would love feedback from the community - especially on the embedding pipeline and audio processing!

Re: MLX-GUI v1.2.4 Private AI API for Apple Silicon (Chat,Audio,Embeddings,Vision)

#3

Post by jki275 » Wed, Jul 23, 2025, 7:17 PM UTC

RamboRogers wrote: post #2

Hey HN! I've been building MLX-GUI as an open-source inference server that turns any Mac into a multi-user AI server. v1.2.4 just shipped with some major additions: Complete Whisper ecosystem (99+ languages, word timestamps, any audio format) 23 embedding models across 13 families (E5, ModernBERT, Arctic, etc.) Mistral Small 24B with vision capabilities OpenAI-compatible API that's actually faster than Ollama on Appl…

It looks pretty cool. How is it different or better than LM Studio?

Re: MLX-GUI v1.2.4 Private AI API for Apple Silicon (Chat,Audio,Embeddings,Vision)

#4

Post by RamboRogers » Sat, Jul 26, 2025, 6:26 AM UTC

jki275 wrote: post #3

RamboRogers wrote: post #2

Hey HN! I've been building MLX-GUI as an open-source inference server that turns any Mac into a multi-user AI server. v1.2.4 just shipped with some major additions: Complete Whisper ecosystem (99+ languages, word timestamps, any audio format) 23 embedding models across 13 families (E5, ModernBERT, Arctic, etc.) Mistral Small 24B with vision capabilities OpenAI-compatible API that's actually faster than Ollama on Appl…

It looks pretty cool. How is it different or better than LM Studio?

Multiple users, automatic model loading, automatic model unloading

Re: MLX-GUI v1.2.4 Private AI API for Apple Silicon (Chat,Audio,Embeddings,Vision)

#5

Post by jki275 » Sat, Jul 26, 2025, 3:53 PM UTC

RamboRogers wrote: post #4

jki275 wrote: post #3

Earlier quoted context omitted.

It looks pretty cool. How is it different or better than LM Studio?

Multiple users, automatic model loading, automatic model unloading

LM Studio does automatic model loading and unloading fyi.

Re: MLX-GUI v1.2.4 Private AI API for Apple Silicon (Chat,Audio,Embeddings,Vision)

#6

Post by RamboRogers » Sat, Jul 26, 2025, 8:32 PM UTC

jki275 wrote: post #5

RamboRogers wrote: post #4

Earlier quoted context omitted.

Multiple users, automatic model loading, automatic model unloading

LM Studio does automatic model loading and unloading fyi.

it's single user and doesn't queue transactions. new transactions replace in process transactions.