Spaces:
Running
Running
Request for gemma-4-12B *base model* in gguf format
#29
by superkuh - opened
Hi. Thanks for converting and quantizing all these models.
Would it be possible for you to convert and quantize the base Gemma-4-12B model? https://huggingface.co/google/gemma-4-12B/tree/main ie, not the fine tuned versions. Just the base model? I, and I imagine others, would really appreciate it for doing normal inference (not training or fine-tuning) but with just pattern completion mode.