Best Local LLM for a 128 GB Mac

Illustration of a desktop Mac and chip with a tall stack of memory sticks

The best local LLM for a 128 GB Mac is gpt-oss 120B, a 65.4 GB download for reasoning, coding and agents. For the hardest reasoning with images, Qwen3.5 122B-A10B (81.4 GB) also fits. All of these run on the Mac itself, with nothing sent to a vendor, in free apps such as Ollama and LM Studio.

Key facts

  • Install first: gpt-oss 120B, 65.4 GB download.
  • Room for a model: about 96 GB of 128 GB, so a file under about 92 GB runs comfortably.
  • App: Ollama or LM Studio, both free. The commands below are for Ollama.
  • Cost: nothing. Check each licence before business use.

On this page

Models that fit a 128 GB Mac

ModelGood forDownloadFit on 128 GBLicenceCommand
gpt-oss 120BReasoning, coding, agents65.4 GBComfortableApache 2.0ollama run gpt-oss:120b
Qwen3.5 122B-A10BHard reasoning, complex tasks, reads images81.4 GBComfortableApache 2.0ollama run qwen3.5:122b-a10b
Llama 4 ScoutLong documents, reads images67.4 GBComfortableLlama 4 Communityollama run llama4:scout
Qwen3-Next 80B-A3BChat, coding, long context50.4 GBComfortableApache 2.0ollama run qwen3-next:80b
Llama 3.3 70BQuality, coding42.5 GBComfortableLlama 3.3 Communityollama run llama3.3

Comfortable means the file fits with room for a long conversation. Tight means it loads, but close other apps and keep chats short. Sizes are what Ollama downloads on a Mac, read from its registry on 21 November 2026. Where Apple's MLX build of a model exists, Ollama now uses it on a Mac, so some sizes differ from the ones on Ollama's website. Have a 96 GB Mac? It gives a model about 72 GB: enough for gpt-oss 120B and Llama 4 Scout, but not Qwen3.5 122B-A10B.

Which one for which job

  • Reasoning, coding and agents: gpt-oss 120B.
  • Hardest reasoning, with images: Qwen3.5 122B-A10B.
  • Very long documents: Llama 4 Scout or Qwen3-Next 80B.
  • Two models loaded at once: Llama 3.3 70B plus a small helper model.

To check any other model against your Mac, use the local LLM memory calculator. For every Mac size on one page, see the best local LLM for Mac.

How much room a 128 GB Mac gives a model

A Mac shares its memory between the processor and the graphics side, and by default macOS lets the graphics side use about 75% of it. On a 128 GB Mac that is about 96 GB. The conversation needs 2 to 4 GB on top of the model file, so a file under about 92 GB runs comfortably and one up to about 94 GB runs if you keep chats short.

Longer documents and longer chats use more memory, so leave more room if you paste in long reports. Speed depends mostly on the chip: a Pro or Max chip moves data faster than a base chip, so the same model answers faster.

Which app to run it in

Ollama runs models in the background for other apps and agents to use; the commands above install and start each model. LM Studio gives you a chat window and a model search. Both are free. See Ollama vs LM Studio if you can't decide.

Frequently asked questions

What is the best local LLM for a 128 GB Mac?

The best local LLM for a 128 GB Mac is gpt-oss 120B, a 65.4 GB download for reasoning, coding and agents. For the hardest reasoning with images, Qwen3.5 122B-A10B (81.4 GB) also fits.

How big a model can a 128 GB Mac run?

By default macOS lets a model use about 96 GB of a 128 GB Mac. Allow 2 to 4 GB for the conversation, so aim for a model file under about 92 GB, or up to 94 GB with short chats.

Are these models free?

Yes, to download and run, with nothing sent to a vendor. Check the licence before business use: Apache 2.0 and MIT allow commercial use, while the Llama, LFM and NVIDIA licences add their own conditions.

Sources

  • Ollama library and registry: model pages, and the download size for a Mac (read 21 November 2026). On my M5 MacBook Air, Ollama 0.40.17 chose the MLX build for Gemma 4 E4B.
  • ModelFit's open hardware dataset (CC BY 4.0), updated 26 October 2026. Good-for labels adapted; fit worked out with my own memory rule.
  • Local LLM memory calculator, for the 75% memory rule

Other Mac sizes: 8 GB · 16 GB · 24 GB · 32 GB · 48 GB · 64 GB.

New models arrive every week. See Local AI This Week for the latest. Spotted something out of date? Tell me.

Scroll to Top