schneiderkamplab/DFM-Mimir-FP4-MLX

DFM-Mimir FP4 (MLX)

This is the 4-bit affine quantized version of DFM-Mimir for use with Apple MLX on Apple Silicon. Converted from the AWQ FP4 checkpoint.

Quantization Details

Loading

from mlx_lm import load, generate

model, tokenizer = load("schneiderkamplab/DFM-Mimir-FP4-MLX")
messages = [
    {"role": "user", "content": "Who are you?"},
]
prompt = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    tokenize=False,
)
response = generate(model, tokenizer, prompt=prompt, max_tokens=40)
print(response)

Model details

Technical Report

Training was performed using a fork of HRM-Text. Further details are provided in our technical report here.

Limitations

Mimir v1 was trained on Danish and English data only. It will likely have poor performance on other languages. The model has not been specifically aligned for safety and may reflect social biases present in its training data.

License

This model is released under the Apache License 2.0.

See the full license text in LICENSE.

Project partners & funding

The development of Mimir v1 was performed in close collaboration between University of Southern Denmark, Aarhus University, University of Copenhagen and the Alexandra Institute, as part of Danish Foundation Models.

Funding was provided by the Ministry of Science, Higher Education and Digital Affairs.

How to cite

@misc{mimir-v1,
  title  = {DFM Mimir v1: An Open HRM Delivering Frontier Performance at 1B Parameters Using Only Permissible Post-Training Data},
  author = {Schneider-Kamp, Peter and Nielsen, Jacob and Barmina, Gicanluca and Enevoldsen, Kenneth and Poech, Lukas Galke},
  year   = {2026},
  url    = {https://huggingface.co/danish-foundation-models/HRM-Mimir-v1}
}