containers/ramalama
1
0
Fork 0
mirror of https://github.com/containers/ramalama.git synced 2026-02-05 06:46:39 +01:00
Code Issues Wiki Activity

docs: Update docs with correct MLX installation instructions

Browse Source 
Signed-off-by: Kush Gupta <kushalgupta@gmail.com>
This commit is contained in:
Kush Gupta
2025-10-13 09:39:53 -04:00
parent f325277346
commit 952ac52969
2 changed files with 10 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
README.md
View File

@@ -141,13 +141,13 @@ The MLX runtime provides optimized inference for Apple Silicon Macs. MLX require
- macOS operating system
- Apple Silicon hardware (M1, M2, M3, or later)
- Usage with `--nocontainer` option (containers are not supported)
- The `mlx-lm` Python package installed on the host system
- The `mlx-lm` uv package installed on the host system as a uv tool
To install and run Phi-4 on MLX, use either `uv` or `pip`:
To install and run Phi-4 on MLX, use `uv`:
```bash
uv pip install mlx-lm
# or pip:
pip install mlx-lm
uv tool install mlx-lm
# or upgrade to the latest version:
uv tool upgrade mlx-lm
ramalama --runtime=mlx serve hf://mlx-community/Unsloth-Phi-4-4bit
```

10
docs/ramalama-serve.1.md
View File

@@ -558,13 +558,13 @@ The MLX runtime is designed for Apple Silicon Macs and provides optimized perfor
- **Operating System**: macOS only
- **Hardware**: Apple Silicon (M1, M2, M3, or later)
- **Container Mode**: MLX requires `--nocontainer` as it cannot run inside containers
- **Dependencies**: Requires `mlx-lm` package to be installed on the host system
- **Dependencies**: The `mlx-lm` uv package installed on the host system as a uv tool
To install MLX dependencies, use either `uv` or `pip`:
To install MLX dependencies, use `uv`:
```bash
uv pip install mlx-lm
# or pip:
pip install mlx-lm
uv tool install mlx-lm
# or upgrade to the latest version:
uv tool upgrade mlx-lm
```
Example usage: