This is a community-quantized 8-bit version of the Qwen3-Coder 30B (with 3B active parameters) model using the MLX framework. It is optimized for local execution on Apple silicon devices and includes a chat template suitable for coding assistance and instruction following. The model is hosted on Hugging Face for developers building local AI coding tools.
Qwen3 Coder 30B A3B Instruct is a Coding AI & assistants product. It focuses on running powerful coding-focused large language models efficiently on Apple Mac hardware. It is built as an open-source project for developers. Qwen3 Coder 30B A3B Instruct is open source under the Open Source license. It runs on the web, the command line, and API.
LM Studio Community builds and maintains Qwen3 Coder 30B A3B Instruct, and the product first shipped in 2025. It operates in a well-populated space: PulseGate tracks 9 similar tools. Key capabilities include code generation, 8-bit quantization, and MLX optimization.
Latest indexed changes and source events
lmstudio-community/Qwen3-Coder-30B-A3B-Instruct-MLX-8bit verified by the PulseGate indexer