@TensComplement The site says "We've been busy", when will the new site be up,

MLX running OpenELM on an iPhone. Thanks for the framework Awni Hannun

Just ported Qwen2.5-VL-3B-Instruct to MLX Swift. Many thanks to Prince Canuma for the Python version from which this is based upon. Awni Hannun I’ll do further testing and send out a PR later this week.

Here is LFM2 from Liquid AI running on mobile with MLX Swift.

Here is LFM2MoE from Liquid AI running on an iPhone 17 Pro. The model here is LFM2-8B-A1-3bit-MLX

Voice on mobile with interruption using Apple’s SpeechAnalyzer, MLX Swift for running the LLM and the following CoreML models: Kokoro, Silero and SegmentAnyText. All running in orchestration. Awni Hannun Fluid Inference

This is Granite 4.0 Nano running on an iPhone 17 Pro with MLX Swift. This is the 350M parameter model and the 1B runs equally well. IBM Developer

@JollaFTW Jolla Tried to place an order with discount which was canceled. I’m no longer able to apply the discount. Any ideas?

Don't have a red nose? That's ok! For every RT we'll donate $10 toward ending child poverty. #RedNose4Kids