GGUF quantization (Q4_K_M) of danish-foundation-models/munin-qwen3.5-9B, a Qwen3.5-9B model post-trained specifically for Danish by Danish Foundation Models.

No official GGUF was published for this checkpoint at the time of conversion, so this was converted locally with llama.cpp's convert_hf_to_gguf.py (--outtype bf16) and llama-quantize (Q4_K_M), for use as the on-device summarization model in transcriber, a Danish meeting transcription app.

License: Apache 2.0, inherited from the base model. See the original model card for details.