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
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

Joseph007fu
/
Ornith-1.0-35B-MTP2-MTPLX

Text Generation
MLX
English
Chinese
mtplx
mtp
mtp2
multi-token-prediction
speculative-decoding
qwen3.5
Mixture of Experts
coding-agent
apple-silicon
q8
Model card Files Files and versions
xet
Community

Instructions to use Joseph007fu/Ornith-1.0-35B-MTP2-MTPLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • MLX

    How to use Joseph007fu/Ornith-1.0-35B-MTP2-MTPLX with MLX:

    # Make sure mlx-lm is installed
    # pip install --upgrade mlx-lm
    # if on a CUDA device, also pip install mlx[cuda]
    
    # Generate text with mlx-lm
    from mlx_lm import load, generate
    
    model, tokenizer = load("Joseph007fu/Ornith-1.0-35B-MTP2-MTPLX")
    
    prompt = "Once upon a time in"
    text = generate(model, tokenizer, prompt=prompt, verbose=True)
  • Notebooks
  • Google Colab
  • Kaggle
  • Local Apps Settings
  • LM Studio
  • MLX LM

    How to use Joseph007fu/Ornith-1.0-35B-MTP2-MTPLX with MLX LM:

    Generate or start a chat session
    # Install MLX LM
    uv tool install mlx-lm
    # Generate some text
    mlx_lm.generate --model "Joseph007fu/Ornith-1.0-35B-MTP2-MTPLX" --prompt "Once upon a time"
  • Atomic Chat
Ornith-1.0-35B-MTP2-MTPLX
898 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 3 commits
Joseph007fu's picture
Joseph007fu
Clarify MTP2 Q8 sidecar title
2daf2a8 verified 24 days ago
  • licenses
    MTP2 acceptance-optimized Q8 sidecar and reproducibility report 24 days ago
  • patches
    MTP2 acceptance-optimized Q8 sidecar and reproducibility report 24 days ago
  • reports
    MTP2 acceptance-optimized Q8 sidecar and reproducibility report 24 days ago
  • scripts
    MTP2 acceptance-optimized Q8 sidecar and reproducibility report 24 days ago
  • .gitattributes
    93 Bytes
    MTP2 acceptance-optimized Q8 sidecar and reproducibility report 24 days ago
  • LICENSE
    11.5 kB
    MTP2 acceptance-optimized Q8 sidecar and reproducibility report 24 days ago
  • NOTICE
    832 Bytes
    MTP2 acceptance-optimized Q8 sidecar and reproducibility report 24 days ago
  • README.md
    7.84 kB
    Clarify MTP2 Q8 sidecar title 24 days ago
  • TECHNICAL_REPORT.md
    8.65 kB
    MTP2 acceptance-optimized Q8 sidecar and reproducibility report 24 days ago
  • artifact-manifest.json
    3.41 kB
    MTP2 acceptance-optimized Q8 sidecar and reproducibility report 24 days ago
  • mtp.safetensors
    897 MB
    xet
    MTP2 acceptance-optimized Q8 sidecar and reproducibility report 24 days ago
  • mtp_config.json
    2.58 kB
    MTP2 acceptance-optimized Q8 sidecar and reproducibility report 24 days ago
  • mtplx_runtime.json
    3.2 kB
    MTP2 acceptance-optimized Q8 sidecar and reproducibility report 24 days ago