mlx-vlm
PulseAugur coverage of mlx-vlm — every cluster mentioning mlx-vlm across labs, papers, and developer communities, ranked by signal.
-
Local VLM pipeline Scribe benchmarked for clinical form data extraction
A new local pipeline called Scribe has been benchmarked for its ability to convert handwritten clinical forms into structured data. The pipeline, designed for offline-first health settings, was tested across nine config…
-
LLMs achieve massive context windows on consumer hardware with new techniques
Researchers are developing innovative methods to enable large language models (LLMs) to handle significantly larger context windows, even on consumer hardware. One approach, JustFit, uses techniques like KV compression …
-
Unofficial Qwen3.8-27B derivatives released with suppressed refusal behavior
PocketAI Model Lab has released a family of unofficial MLX derivatives of the Qwen/Qwen3.8-27B model. These variants, including 2-bit AWQ, 4-bit, 6-bit, 8-bit, and BF16 versions, have been modified to suppress learned r…
-
Nativ app enables local AI model execution on Mac
Nativ is a new macOS desktop application that allows users to run AI models locally on their Macs. Developed by Prince Canuma, the creator of the MLX-VLM Python library, Nativ utilizes MLX to provide both a chat interfa…
-
Nativ brings local LLM inference to Apple Silicon Macs
Nativ is a new open-source application designed to run large language models locally on Apple Silicon Macs. It emphasizes privacy and offline use, with no cloud dependency or subscription fees. The application is built …
-
MiniMax M3 Q4 model completes US customs form on Mac Studio
MiniMax AI has demonstrated its M3 Q4 model running locally on a Mac Studio M3 Ultra. The open-weight model successfully processed a US customs form using the MLX-VLM framework, extracting information from an ID card ph…
-
MiniMax M3 Model Optimized for Faster Decoding on MLX-VLM
MiniMax AI's MiniMax M3 model has seen community-driven optimizations for faster decoding on the MLX-VLM framework. These improvements aim to reduce the model's footprint while enhancing its speed. The contributions wer…
-
MiniMax AI Celebrates Community Contributions to M3 Open Weights
MiniMax AI is celebrating the open-source community's work with its M3 open weights. The mlx-vlm project has integrated support for MiniMax M3, including an implementation for Modern Standard Arabic. This integration wa…