Llama
4 MLX aliases · Meta's Llama 3 / 3.1 · 1B / 3B / 8B.
Pick one
One command per line of this family, smallest download first. Your Mac needs the download size in free memory plus room for macOS and the context window; the hardware tiers page has the engine's picks for every RAM size. The first run downloads the weights and starts an OpenAI-compatible server on http://localhost:8000/v1.
rapid-mlx serve llama3-1b-4bit
Meta's Llama line — we ship the small / mid tier of the Llama 3 family (1B / 3B / 8B) as a stable baseline. Uses the llama tool-call parser for Llama-style <|python_tag|> function-call envelopes.
- family
- Llama
- aliases
- 4
- lines
- 1
- install
- rapid-mlx serve <alias>
- OpenAI base URL
- http://localhost:8000/v1
Download
Every alias on this page downloads with one command — the pull buttons in the tables below copy it. All 4 aliases on this page are mirrored on the rapid-mlx CDN — with automatic mid-pull fallback to Hugging Face if a mirror file slows down. Weights land in the standard Hugging Face cache, and rapid-mlx serve pulls automatically on first use. Live mirror status →
Llama 3 / 3.1 · 4 aliases
Small / mid tier of the Llama 3 family (1B / 3B / 8B). Stable baseline with the llama tool-call parser for the <|python_tag|> function-call envelope.
parser: llama
| alias | hf repo | tool parser | reasoning | flags | context | AA index | get it |
|---|---|---|---|---|---|---|---|
| llama-3.1-8b-4bit | mlx-community/Meta-Llama-3.1-8B-Instruct-4bit | llama | — | spec | 128K | 7.4 | CDN |
| llama-3.1-8b-8bit | mlx-community/Meta-Llama-3.1-8B-Instruct-8bit | llama | — | spec | 128K | 7.4 | CDN |
| llama3-1b-4bit | mlx-community/Llama-3.2-1B-Instruct-4bit | llama | — | spec | 128K | 1 | CDN |
| llama3-3b-4bit | mlx-community/Llama-3.2-3B-Instruct-4bit | llama | — | spec | 128K | 3.9 | CDN |
Notes & caveats
- Llama 3.1 8B 8-bit is the recommended pick for general use on a 16 GB+ Mac.
Context is read from the config.json of the exact build each alias pulls; for an embedding model it is the most input tokens the engine embeds, which can be less than the config declares. AA index is the Artificial Analysis Intelligence Index for the base model at full precision with reasoning on — a property of the model, not a score for our quantised build.