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

majentik
/
UEmbed-4B-MLX-4bit

Feature Extraction
MLX
Safetensors
qwen3_5
quantized
4-bit precision
apple-silicon
uembed
embeddings
text-embedding
Model card Files Files and versions
xet
Community

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

  • Libraries
  • MLX

    How to use majentik/UEmbed-4B-MLX-4bit with MLX:

    # Download the model from the Hub
    pip install huggingface_hub[hf_xet]
    
    huggingface-cli download --local-dir UEmbed-4B-MLX-4bit majentik/UEmbed-4B-MLX-4bit
  • Notebooks
  • Google Colab
  • Kaggle
  • Local Apps Settings
  • LM Studio
  • Atomic Chat
UEmbed-4B-MLX-4bit
3.18 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 3 commits
majentik's picture
majentik
Re-gate and publish: parity fixed (harness open-think template; stock mlx-lm) β€” bf16 parity >=0.999967, 4bit gs32 gate cos-vs-bf16 0.9441, ordering PASS
519a47a verified 4 days ago
  • .gitattributes
    1.57 kB
    UEmbed-4B MLX 4bit β€” PRIVATE hold pending mlx-lm grouped-value gated-delta fix 4 days ago
  • README.md
    4.55 kB
    Re-gate and publish: parity fixed (harness open-think template; stock mlx-lm) β€” bf16 parity >=0.999967, 4bit gs32 gate cos-vs-bf16 0.9441, ordering PASS 4 days ago
  • chat_template.jinja
    7.76 kB
    UEmbed-4B MLX 4bit β€” PRIVATE hold pending mlx-lm grouped-value gated-delta fix 4 days ago
  • config.json
    3.01 kB
    UEmbed-4B MLX 4bit β€” PRIVATE hold pending mlx-lm grouped-value gated-delta fix 4 days ago
  • model.safetensors
    3.16 GB
    xet
    UEmbed-4B MLX 4bit β€” PRIVATE hold pending mlx-lm grouped-value gated-delta fix 4 days ago
  • model.safetensors.index.json
    81 kB
    UEmbed-4B MLX 4bit β€” PRIVATE hold pending mlx-lm grouped-value gated-delta fix 4 days ago
  • tokenizer.json
    20 MB
    xet
    UEmbed-4B MLX 4bit β€” PRIVATE hold pending mlx-lm grouped-value gated-delta fix 4 days ago
  • tokenizer_config.json
    1.21 kB
    UEmbed-4B MLX 4bit β€” PRIVATE hold pending mlx-lm grouped-value gated-delta fix 4 days ago