This is a GGUF-quantized release of a 12B parameter model derived from Gemma-4, optimized for local inference. It includes multiple quantization levels (Q4, Q6, Q8, FP16) and supports reasoning traces. The model is hosted on Hugging Face and is intended for use with GGUF-compatible runtimes such as llama.cpp.
Gemmable 4 12B MTP is a Foundation models & chat project. It focuses on running large reasoning-capable language models locally with reduced memory requirements. It is built as an open-source project for developers. The project is open source (Open Source). It ships for the web, the command line, and API.
It is developed by Mia-AiLab, and it first shipped in 2025. Key capabilities include GGUF Quantization, Reasoning Traces, and Local Inference.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do