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

RoderickQiu
/
kev-4b-mlx-8bit

MLX
Safetensors
qwen3_5
kev
system-one
typed-decisions
8-bit precision
apple-silicon
Eval Results (legacy)
Model card Files Files and versions
xet
Community

Instructions to use RoderickQiu/kev-4b-mlx-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • MLX

    How to use RoderickQiu/kev-4b-mlx-8bit with MLX:

    # Download the model from the Hub
    pip install huggingface_hub[hf_xet]
    
    huggingface-cli download --local-dir kev-4b-mlx-8bit RoderickQiu/kev-4b-mlx-8bit
  • Notebooks
  • Google Colab
  • Kaggle
  • Local Apps Settings
  • LM Studio
  • Atomic Chat
kev-4b-mlx-8bit
4.5 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 10 commits
RoderickQiu's picture
RoderickQiu
Add the 119 trial pages: 8-bit against bf16 on this checkpoint
6929ac3 verified 2 days ago
  • .gitattributes
    1.57 kB
    Kev-4B merged and quantized to 8 bits for MLX 5 days ago
  • LICENSE
    11.3 kB
    Kev-4B merged and quantized to 8 bits for MLX 5 days ago
  • README.md
    8.34 kB
    Add the 119 trial pages: 8-bit against bf16 on this checkpoint 2 days ago
  • added_tokens.json
    707 Bytes
    Kev-4B merged and quantized to 8 bits for MLX 5 days ago
  • config.json
    2.75 kB
    Kev-4B merged and quantized to 8 bits for MLX 5 days ago
  • head.pt
    5.25 MB
    xet
    Kev-4B 139fdd94: 8-bit weights, head, and development-suite card 2 days ago
  • merges.txt
    1.67 MB
    Kev-4B merged and quantized to 8 bits for MLX 5 days ago
  • model.safetensors
    4.47 GB
    xet
    Kev-4B 139fdd94: 8-bit weights, head, and development-suite card 2 days ago
  • provenance.json
    889 Bytes
    Kev-4B 139fdd94: 8-bit weights, head, and development-suite card 2 days ago
  • special_tokens_map.json
    616 Bytes
    Kev-4B merged and quantized to 8 bits for MLX 5 days ago
  • tokenizer.json
    20 MB
    xet
    Kev-4B merged and quantized to 8 bits for MLX 5 days ago
  • tokenizer_config.json
    1.13 kB
    Kev-4B merged and quantized to 8 bits for MLX 5 days ago
  • vocab.json
    2.78 MB
    Kev-4B merged and quantized to 8 bits for MLX 5 days ago