A 4-bit quantized version of Qwen2.5-Coder-14B-Instruct optimized for the MLX framework on Apple Silicon. It supports code generation, instruction following, and tool calling. The model is distributed in a format suitable for local execution via MLX or compatible runners like LM Studio.
Qwen2.5 Coder 14B Instruct sits in PulseGate's Coding AI & assistants category. It focuses on running a powerful code-specialized 14B LLM locally on Apple Silicon hardware with low memory usage. It is built as an open-source project for developers. Qwen2.5 Coder 14B Instruct is open source under the Open Source license. The product ships for the web, the command line, and API.
lmstudio-community builds and maintains Qwen2.5 Coder 14B Instruct, and the product first shipped in 2024. It operates in a well-populated space: PulseGate tracks 6 similar tools. Key capabilities include code generation, tool calling, and MLX format.
Latest indexed changes and source events
lmstudio-community/Qwen2.5-Coder-14B-Instruct-MLX-4bit verified by the PulseGate indexer
Other apps tracked under the same category.
