Models · family
Llama
4 MLX aliases · Meta's Llama 3 / 3.1 · 1B / 3B / 8B.
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
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 |
|---|---|---|---|---|
| llama-3.1-8b-4bit | mlx-community/Meta-Llama-3.1-8B-Instruct-4bit | llama | — | spec |
| llama-3.1-8b-8bit | mlx-community/Meta-Llama-3.1-8B-Instruct-8bit | llama | — | spec |
| llama3-1b-4bit | mlx-community/Llama-3.2-1B-Instruct-4bit | llama | — | spec |
| llama3-3b-4bit | mlx-community/Llama-3.2-3B-Instruct-4bit | llama | — | spec |
Notes & caveats
- Llama 3.1 8B 8-bit is the recommended pick for general use on a 16 GB+ Mac.
- Llama 3 1B 4-bit is excellent as a draft model for speculative decoding against Llama 3.1 8B.