DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to run large Llama-style models on a Mac with AirLLM with Airllm

Install mlx and torch and run AirLLM on Apple Silicon for supported model architectures.

Short answer: Install mlx and torch on your Mac; then run pip install airllm; pick a Llama-style model; only LlamaForCausalLM and MistralForCausalLM run on macOS for now. All steps.

Who it is forA Mac user who wants to try large open models without an NVIDIA GPU.

The problemMost large-model tooling assumes CUDA and does not run on Macs.

The outcomeA Llama-style model running on your Mac through AirLLM's macOS support.

What you need first

  • Python and pip
  • A CUDA GPU (a few GB of VRAM) or a Mac with mlx and torch for Llama-style models
  • Lots of disk for split layer shards; some models need specific transformers versions
  • Optional: bitsandbytes for compression

Steps

  1. Install mlx and torch on your Mac
  2. Run pip install airllm
  3. Pick a Llama-style model; only LlamaForCausalLM and MistralForCausalLM run on macOS for now
  4. Follow the run_on_macos example notebook from the README
  5. Generate text and check memory use while it runs

Prompt for your agent

Set up lyogavin/airllm on my Mac with mlx and torch, choose a Llama-style model that is supported on macOS, run the macOS example with <prompt>, and report memory use and time per token.

Caveat. Other architectures raise an error on macOS before anything is downloaded.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for lyogavin/airllm and "Run large Llama-style models on a Mac with AirLLM"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer