Gemma 4 12B Social Post LoRA GGUF
LM Studio-compatible GGUF export of micic-mihajlo/gemma-4-12b-social-post-lora, merged into google/gemma-4-12B and quantized with llama.cpp Q4_K_M.
Files
gemma-4-12b-social-post-lora.Q4_K_M.gguf- quantized text-generation GGUF for LM Studio / llama.cpp.conversion_manifest.json- source repos and conversion settings.
Source
- Base model:
google/gemma-4-12B - LoRA adapter:
micic-mihajlo/gemma-4-12b-social-post-lora - Conversion: current
ggml-org/llama.cppconvert_hf_to_gguf.py - Quantization:
Q4_K_M
LM Studio
In LM Studio, use the Hugging Face downloader with:
https://huggingface.co/micic-mihajlo/gemma-4-12b-social-post-lora-GGUF