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

droyster
/
Qwen3.5-4B-Text-MLX-4bit

MLX
Safetensors
qwen3_5
text-only
faster-context
4-bit precision
Model card Files Files and versions
xet
Community

Instructions to use droyster/Qwen3.5-4B-Text-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • MLX

    How to use droyster/Qwen3.5-4B-Text-MLX-4bit with MLX:

    # Download the model from the Hub
    pip install huggingface_hub[hf_xet]
    
    huggingface-cli download --local-dir Qwen3.5-4B-Text-MLX-4bit droyster/Qwen3.5-4B-Text-MLX-4bit
  • Notebooks
  • Google Colab
  • Kaggle
  • Local Apps Settings
  • LM Studio
  • Atomic Chat
Qwen3.5-4B-Text-MLX-4bit
2.39 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 2 commits
droyster's picture
droyster
Qwen3.5-4B 4-bit MLX, vision tower stripped (2.9->2.2 GB, logit-parity 0.0)
c229db3 verified 12 days ago
  • .gitattributes
    1.57 kB
    Qwen3.5-4B 4-bit MLX, vision tower stripped (2.9->2.2 GB, logit-parity 0.0) 12 days ago
  • README.md
    1.31 kB
    Qwen3.5-4B 4-bit MLX, vision tower stripped (2.9->2.2 GB, logit-parity 0.0) 12 days ago
  • chat_template.jinja
    7.76 kB
    Qwen3.5-4B 4-bit MLX, vision tower stripped (2.9->2.2 GB, logit-parity 0.0) 12 days ago
  • config.json
    2.44 kB
    Qwen3.5-4B 4-bit MLX, vision tower stripped (2.9->2.2 GB, logit-parity 0.0) 12 days ago
  • model.safetensors
    2.37 GB
    xet
    Qwen3.5-4B 4-bit MLX, vision tower stripped (2.9->2.2 GB, logit-parity 0.0) 12 days ago
  • model.safetensors.index.json
    77.3 kB
    Qwen3.5-4B 4-bit MLX, vision tower stripped (2.9->2.2 GB, logit-parity 0.0) 12 days ago
  • tokenizer.json
    20 MB
    xet
    Qwen3.5-4B 4-bit MLX, vision tower stripped (2.9->2.2 GB, logit-parity 0.0) 12 days ago
  • tokenizer_config.json
    1.14 kB
    Qwen3.5-4B 4-bit MLX, vision tower stripped (2.9->2.2 GB, logit-parity 0.0) 12 days ago
  • vocab.json
    6.72 MB
    Qwen3.5-4B 4-bit MLX, vision tower stripped (2.9->2.2 GB, logit-parity 0.0) 12 days ago