Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets
  • 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

litert-community
/
Kimi-Linear-48B-A3B-Instruct

Text Generation
LiteRT-LM
English
litertlm
kimi
kimi-linear
Mixture of Experts
Model card Files Files and versions
xet
Community

Instructions to use litert-community/Kimi-Linear-48B-A3B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • LiteRT-LM

    How to use litert-community/Kimi-Linear-48B-A3B-Instruct with LiteRT-LM:

    # LiteRT-LM runs on various platforms (Android, iOS, Windows, Linux, macOS, IoT, Web/WASM)
    # and supports many APIs (C++, Python, Kotlin, Swift, JavaScript, Flutter).
    # For platform-specific integration guides, please refer to the official developer website:
    # https://ai.google.dev/edge/litert-lm
    
    # To try LiteRT-LM, the easiest way is to use our CLI tool.
    # 1. Install the LiteRT-LM CLI tool:
    pip install -U litert-lm
    
    # 2. Download and run this model locally:
    # See: https://ai.google.dev/edge/litert-lm/cli
    # A single .litertlm file in the repo is picked automatically; otherwise the CLI asks which one to run
    # (or pass its name right after the repo id).
    litert-lm run \
      --from-huggingface-repo=litert-community/Kimi-Linear-48B-A3B-Instruct \
      --prompt="Write me a poem"
  • Notebooks
  • Google Colab
  • Kaggle
Kimi-Linear-48B-A3B-Instruct
106 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 7 commits
mlboydaisuke's picture
mlboydaisuke
DETAILS: the conversion scripts and the rebuild of both files from them on 2026-11-15 (every byte after the 16,384-byte header is the published one); LiteRT-LM 0.19.2 is still the latest PyPI release
46eb9f0 verified about 3 hours ago
  • .gitattributes
    1.69 kB
    Add the int8 file kimi_linear_48b_a3b_int8_ekv4096.litertlm (CPU and WebGPU) and update the model card 1 day ago
  • DETAILS.md
    16.4 kB
    DETAILS: the conversion scripts and the rebuild of both files from them on 2026-11-15 (every byte after the 16,384-byte header is the published one); LiteRT-LM 0.19.2 is still the latest PyPI release about 3 hours ago
  • README.md
    7.02 kB
    DETAILS: the conversion scripts and the rebuild of both files from them on 2026-11-15 (every byte after the 16,384-byte header is the published one); LiteRT-LM 0.19.2 is still the latest PyPI release about 3 hours ago
  • kimi_linear_48b_a3b_int8_ekv4096.litertlm
    50.5 GB
    xet
    Add the int8 file kimi_linear_48b_a3b_int8_ekv4096.litertlm (CPU and WebGPU) and update the model card 1 day ago
  • kimi_linear_48b_a3b_mixed_int8_cpu_ekv4096.litertlm
    55.3 GB
    xet
    Add Kimi-Linear-48B-A3B-Instruct for LiteRT-LM (CPU file) and the model card 3 days ago
  • litertlm_manifest.json
    20.4 kB
    litertlm_manifest.json: add the int8 file kimi_linear_48b_a3b_int8_ekv4096.litertlm 1 day ago