Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

strumecki
/
moshika-mlx-mp

MLX
Moshi
English
speech
audio
conversational
quantized
mixed-precision
Model card Files Files and versions
xet
Community

Instructions to use strumecki/moshika-mlx-mp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • MLX

    How to use strumecki/moshika-mlx-mp with MLX:

    # Download the model from the Hub
    pip install huggingface_hub[hf_xet]
    
    huggingface-cli download --local-dir moshika-mlx-mp strumecki/moshika-mlx-mp
  • Moshi

    How to use strumecki/moshika-mlx-mp with Moshi:

    # pip install moshi_mlx
    # Run local inference (macOS Apple Silicon)
    python -m moshi_mlx.local --hf-repo "strumecki/moshika-mlx-mp"
    
    # Or run with web UI
    python -m moshi_mlx.local_web --hf-repo "strumecki/moshika-mlx-mp"
  • Notebooks
  • Google Colab
  • Kaggle
  • Local Apps
  • LM Studio
moshika-mlx-mp
5.29 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 3 commits
strumecki's picture
strumecki
Add model card
be8296a verified 14 days ago
  • .gitattributes
    1.52 kB
    initial commit 14 days ago
  • README.md
    2.88 kB
    Add model card 14 days ago
  • model.mp.safetensors
    5.29 GB
    xet
    Mixed-precision Moshi 7B (q4 bulk + q8 sensitive) 14 days ago