smpanaro / apple-silicon-4bit-quantLinks
Supporting code for "LLMs for your iPhone: Whole-Tensor 4 Bit Quantization"
☆11Updated last year
Alternatives and similar repositories for apple-silicon-4bit-quant
Users that are interested in apple-silicon-4bit-quant are comparing it to the libraries listed below
Sorting:
- ModernBERT model optimized for Apple Neural Engine.☆28Updated 11 months ago
- 1.58 Bit LLM on Apple Silicon using MLX☆226Updated last year
- Profile your CoreML models directly from Python 🐍☆29Updated 3 months ago
- Find out why your CoreML model isn't running on the Neural Engine!☆27Updated last year
- SmolVLM2 Demo☆179Updated 8 months ago
- Advanced Ultra-Low Bitrate Compression Techniques for the LLaMA Family of LLMs☆110Updated last year
- QuIP quantization☆61Updated last year
- ☆219Updated 10 months ago
- mlx image models for Apple Silicon machines☆87Updated last week
- ☆52Updated last year
- Repo hosting codes and materials related to speeding LLMs' inference using token merging.☆37Updated 2 months ago
- ☆111Updated 3 weeks ago
- C API for MLX☆154Updated last week
- KAN (Kolmogorov–Arnold Networks) in the MLX framework for Apple Silicon☆31Updated 5 months ago
- ☆64Updated 5 months ago
- Implementation of nougat that focuses on processing pdf locally.☆83Updated 10 months ago
- ☆120Updated last year
- Thin wrapper around GGML to make life easier☆40Updated last month
- ☆14Updated last year
- RWKV-7: Surpassing GPT☆100Updated last year
- ☆158Updated 5 months ago
- Work in progress.☆75Updated 2 weeks ago
- PB-LLM: Partially Binarized Large Language Models☆157Updated 2 years ago
- Inference of Mamba models in pure C☆194Updated last year
- Distributed Inference for mlx LLm☆99Updated last year
- A safetensors extension to efficiently store sparse quantized tensors on disk☆214Updated this week
- ☆51Updated last year
- Simple high-throughput inference library☆150Updated 6 months ago
- MLX support for the Open Neural Network Exchange (ONNX)☆62Updated last year
- An efficent implementation of the method proposed in "The Era of 1-bit LLMs"☆155Updated last year