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

bearzi
/
MiMo-V2.5-MLX

MLX
mimo_v2_block_fp8
apple-silicon
mimo_v2
block_fp8
Mixture of Experts
custom_code
fp8
Model card Files Files and versions
xet
Community

Instructions to use bearzi/MiMo-V2.5-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • MLX

    How to use bearzi/MiMo-V2.5-MLX with MLX:

    # Download the model from the Hub
    pip install huggingface_hub[hf_xet]
    
    huggingface-cli download --local-dir MiMo-V2.5-MLX bearzi/MiMo-V2.5-MLX
  • Notebooks
  • Google Colab
  • Kaggle
  • Local Apps Settings
  • LM Studio
MiMo-V2.5-MLX
312 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 9 commits
bearzi's picture
bearzi
Fix YAML front matter (license/base_model/tags metadata)
b3da254 verified 24 days ago
  • .gitattributes
    1.52 kB
    initial commit about 1 month ago
  • LICENSE
    1.4 kB
    initial: model code, converter, config, tokenizer, docs about 1 month ago
  • NOTICE
    1.18 kB
    initial: model code, converter, config, tokenizer, docs about 1 month ago
  • README.md
    5.05 kB
    Fix YAML front matter (license/base_model/tags metadata) 24 days ago
  • config.json
    7.79 kB
    initial: model code, converter, config, tokenizer, docs about 1 month ago
  • convert_mimo.py
    10.2 kB
    initial: model code, converter, config, tokenizer, docs about 1 month ago
  • generation_config.json
    195 Bytes
    initial: model code, converter, config, tokenizer, docs about 1 month ago
  • mimo_v2.5_block_fp8.safetensors
    312 GB
    xet
    weights: MoE-stacked repack of XiaomiMiMo/MiMo-V2.5 (text-only) about 1 month ago
  • mimo_v2_block_fp8.py
    18 kB
    Fork-free model file: standalone layers + gather_qmv_fast decode, no native block_fp8 mode (runs on stock MLX) 24 days ago
  • tokenizer.json
    7.03 MB
    initial: model code, converter, config, tokenizer, docs about 1 month ago
  • tokenizer_config.json
    15.2 kB
    initial: model code, converter, config, tokenizer, docs about 1 month ago