Llama 3.3 70B Instruct is a 70-billion-parameter text model from Meta, tuned for multilingual dialogue in English, German, French, Italian, Portuguese, Hindi, Spanish and Thai, with a 128K-token context.
A 4-bit MLX build is about 40 GB; on mlx.app's estimate it needs a Mac with 64 GB of memory. All 70 billion parameters work on every token, so it writes slowly next to mixture-of-experts models.
Open weights under the Llama 3.3 Community License, a custom licence with conditions; Meta's repository asks you to accept it before downloading. Run locally, nothing leaves your Mac.
How to Get It
Official downloads only. MLX never re-hosts an app, and never runs a command for you.
MLX Score
Ranked against the open models listings, from real public data only. How the score works.
Information
- Developer
- Meta
- Category
- Open models
- Price
- Free (Open weights, free to download.)
- Your data
- Runs on your Mac
- Licence
- Llama 3.3 Community License
- Mac
- macOS 14.0 or later
- iPhone and iPad
- —
- Needs
- 64 GB memory
- Links
- Website · Hugging Face
- Facts checked
- 2026-11-01
Sources
You Might Also Like
Gemma 4 31BModels
gpt-oss-20bModels
Llama 3.1 8B InstructModels
Qwen3.5 9BModels
Qwen3.6 35B A3BModels
DeepSeek V4 Flash 0731Models
gpt-oss-120bModels
Gemma 4 E4BModels
Qwen3.6 27BModels
Nemotron 3 Nano 30B A3BModels
GLM-4.7 FlashModels
Qwen3 Coder 30B A3B InstructModelsLlama 3.3 70B Instruct is a product of Meta; MLX isn’t affiliated with it. Something wrong? Write to support@mlx.app.