Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

tritesh
/
dflash-mlx-universal

Text Generation
MLX
dflash-mlx-universal
speculative-decoding
diffusion
dflash
inference-acceleration
apple-silicon
qwen3
llama
mistral
gemma
block-diffusion
Model card Files Files and versions
xet
Community

Instructions to use tritesh/dflash-mlx-universal with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • MLX

    How to use tritesh/dflash-mlx-universal 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("tritesh/dflash-mlx-universal")
    
    prompt = "Once upon a time in"
    text = generate(model, tokenizer, prompt=prompt, verbose=True)
  • Notebooks
  • Google Colab
  • Kaggle
  • Local Apps
  • LM Studio
  • MLX LM

    How to use tritesh/dflash-mlx-universal with MLX LM:

    Generate or start a chat session
    # Install MLX LM
    uv tool install mlx-lm
    # Generate some text
    mlx_lm.generate --model "tritesh/dflash-mlx-universal" --prompt "Once upon a time"
dflash-mlx-universal / examples
10.5 kB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 1 commit
tritesh's picture
tritesh
Upload folder using huggingface_hub
0433390 verified 1 day ago
  • __init__.py
    31 Bytes
    Upload folder using huggingface_hub 1 day ago
  • convert_drafter.py
    2.51 kB
    Upload folder using huggingface_hub 1 day ago
  • qwen3_4b_demo.py
    2.5 kB
    Upload folder using huggingface_hub 1 day ago
  • train_custom_drafter.py
    5.41 kB
    Upload folder using huggingface_hub 1 day ago