This is a 5-bit quantized version of Google's Gemma-4 26B model (A4B instruction-tuned variant) optimized for the MLX framework. It is hosted on Hugging Face and designed for local inference on Apple Silicon hardware, allowing developers to run a capable language model with significantly reduced memory footprint compared to the original.
Gemma 4 26B A4B It is a Foundation models & chat product. It focuses on running large language models locally with reduced memory requirements. It is built as an open-source project for developers and AI researchers. Gemma 4 26B A4B It is open source under the MIT license. Gemma 4 26B A4B It is available on the web, the command line, and API.
lmstudio-community builds and maintains Gemma 4 26B A4B It, and the product first shipped in 2024. Development happens publicly on GitHub with 5.2k stars and 418 commits in the last 90 days. The category is crowded — PulseGate's index counts 24 comparable apps. Key capabilities include quantized weights, MLX optimization, and instruction tuned.
Latest indexed changes and source events
lmstudio-community/gemma-4-26B-A4B-it-MLX-5bit verified by the PulseGate indexer
Other apps tracked under the same category.
