What you need to run Llama 3.3 70B

About Llama 3.3 70B

Llama 3.3 70B is a general chat model from Meta. Older but solid large model. Needs serious memory. Running it locally needs about 45.6 GB of memory, and the download is 43 GB.

Smallest Mac that runs it

The least memory you need, by Apple chip:

• M1: does not fit
• M1 Pro: does not fit
• M1 Max: does not fit
• M1 Ultra: from 64 GB
• M2: does not fit
• M2 Pro: does not fit
• M2 Max: does not fit
• M2 Ultra: from 64 GB
• M3: does not fit
• M3 Pro: does not fit
• M3 Max: does not fit
• M3 Ultra: from 96 GB
• M4: does not fit
• M4 Pro: does not fit
• M4 Max: from 64 GB
• M5: does not fit
• M5 Pro: does not fit
• M5 Max: from 64 GB

Graphics cards

No single desktop graphics card runs it well. Runs slowly with help from system RAM on: RTX 5090.

Hardware to run it

As an Amazon Associate I earn from qualifying purchases.

• Smallest Mac: M5 Max with 64 GB. See it on Amazon
• No single desktop graphics card runs it well.
• Storage: this model is a 43 GB download, and most people end up keeping several. A fast external SSD keeps your main drive free. See SSDs on Amazon

Lighter and heavier alternatives

• Gemma 4 31B: needs about 21.5 GB, a lighter choice. One of the best models that fits a 24 GB GPU or 32 GB Mac.
• Qwen 3.5 35B A3B: needs about 23.6 GB, a lighter choice. Very fast for its size. Great general assistant.
• gpt-oss 120B: needs about 68.8 GB, a heavier choice. OpenAI's big open model. Fast for its size on high-memory machines.
• Qwen 3.5 122B A10B: needs about 85.5 GB, a heavier choice. Near frontier quality at home, if you have 96 GB or more.

Questions