This is an unofficial Q4_K_S GGUF quantization of
JetBrains/Mellum2-12B-A2.5B-Thinking.
The original model was released by JetBrains under the Apache 2.0 license. This repository only provides a GGUF quantized version for use with llama.cpp and compatible runtimes.
1./build/bin/llama-quantize \
2 mellum2-thinking-BF16.gguf \
3 Mellum2-12B-A2.5B-Thinking-Q4_K_S.gguf \
4 Q4_K_S
The original model is released under the Apache 2.0 license.
This GGUF quantization is provided under the same Apache 2.0 license. See the LICENSE file for details.
