Google added native support for Gemma 4 Multi-Token Prediction (MTP) to LiteRT-LM, its on-device LLM runtime built on LiteRT (formerly TensorFlow Lite). Google reports the integration yields MTP decod…
Google released Magenta RealTime 2, an open-weights AI model and real-time inference engine that enables live, low-latency music generation on a MacBook. The model responds instantly to MIDI, audio, a…
A new open-source benchmark, "apple-silicon-llm-bench," reveals that Google's LiteRT-LM runtime outperforms MLX-Swift on the iPhone 17 Pro for Gemma 4 E2B inference, achieving 55.4 tok/s with 4.5x les…
Google DeepMind released Gemma 4 12B, an encoder-free multimodal model that processes text, images, audio, and video natively without separate vision or audio encoders. The 12-billion-parameter model …
Liquid AI released LFM2.5-8B-A1B, an edge model designed for fast tool calling on consumer hardware, with a 128K context window and pretraining scaled to 38 trillion tokens. The model, available on Hu…
Ollama released version 0.30.0-rc23, a pre-release that shifts the software's architecture to directly support llama.cpp instead of building on top of GGML, and adds compatibility with the GGUF file f…
OpenAI's cloud-based Chronicle service, which incurred per-frame costs for analyzing screen captures, with a local Gemma 4 E4B 4-bit MLX model running on a $599 Mac mini. This new setup processes vide…
The ExecuTorch MLX delegate now enables GPU-accelerated inference for PyTorch models on Apple Silicon Macs through Apple's MLX framework. The new backend achieves 3-6x higher throughput on generative …
The article provides instructions for running Claude Code using a local large language model (LLM) instead of Anthropic's cloud-based models. It recommends downloading specific quantized Qwen3.6 model…