by riccardomusmeci · AI 工具 · ★ 468
mlx-llm Large Language Models (LLMs) applications and tools running on Apple Silicon in real-time with Apple MLX. Go to the entire Youtube Video. How to install 🔨 Models 🧠 Currently, out-of-the-box supported models are: To create a model with pre-trained weights from HuggingFace: You can also load a new version of pre-trained weights for a specific model directly from HuggingFace: set by adding before the HuggingFace repository if necessary, specify custom model configs (ropetheta, ropetraditional, vocabsize, normeps) Here's an example of how to to it: Quantization 📉 To quantize a model...
| Stars | 468 |
| Forks | 27 |
| Language | Python |
| Category | AI 工具 |
| Quality Score | 63.0133906437189/100 |
| Open Issues | 1 |
| Last Updated | 2025-01-29 |
| Created | 2023-12-07 |
| Platforms | python |
| Est. Tokens | ~127k |
These tools work well together with mlx-llm for enhanced workflows:
Explore other popular ai 工具 tools:
mlx-llm is Large Language Models (LLMs) applications and tools running on Apple Silicon in real-time with Apple MLX.. It is categorized as a AI 工具 with 468 GitHub stars.
mlx-llm is primarily written in Python. It covers topics such as llama, llm, mistral.
You can find installation instructions and usage details in the mlx-llm GitHub repository at github.com/riccardomusmeci/mlx-llm. The project has 468 stars and 27 forks, indicating an active community.