Grux AI Download

Which local LLM is best for coding on my Mac?

The best local coding model is the largest code-tuned model your Mac's memory holds: Qwen 2.5 Coder from 8 GB up, and Qwen 3 Coder 30b from about 48 GB. Qwen 2.5 Coder comes in 3b (1.9GB), 7b (4.7GB), 14b (9.0GB) and 32b (20GB) sizes with a 32K context window. Qwen 3 Coder 30b is a 19GB download with a 256K context window, built for agentic coding, and Grux AI's own catalogue estimates it needs about one and a half times its download in memory, which is why it wants a 48 GB Mac. The full Qwen 3 Coder, 480b at 290GB, is beyond any Mac. All of them run through Ollama with one command. Grux AI (MIT) lists Qwen 3 Coder in its Local Models catalogue and recommends what fits the Mac it runs on; it is not a code editor, but it can hand a change to the coding agent you already use.

Download Grux AI 3.3.1, free, for macOS 14 or later on Apple silicon.

Grux AI 3.3.1 · last checked 2026-11-13 · generated from the shipping release

Which model fits which Mac

Your Mac's memoryCoding modelDownload
8 GBQwen 2.5 Coder 3b1.9GB
16 GBQwen 2.5 Coder 7b4.7GB
24 GBQwen 2.5 Coder 14b9.0GB
32 GBQwen 2.5 Coder 14b; the 32b is tight9.0GB, 20GB
48 GBQwen 3 Coder 30b, Tight; or Qwen 2.5 Coder 32b19GB, 20GB
64 GB or moreQwen 3 Coder 30b, a good fit19GB

The table is a rough guide from file size, taken from the sizes on Ollama's Qwen 2.5 Coder and Qwen 3 Coder pages, read on 4 October 2026. The which LLM can my Mac run page rates by the memory a model uses while running, which is larger than the file, so it is the rating to trust near your Mac's limit.

brew install ollama
ollama run qwen2.5-coder:14b   # 9.0GB, 24 GB Macs
ollama run qwen3-coder         # 30b, 19GB, 48 GB Macs

Where to check this

ClaimSource
Qwen 2.5 Coder sizes 3b to 32b, 32K contextOllama library, qwen2.5-coder
Qwen 3 Coder 30b is 19GB with a 256K context; the 480b is 290GBOllama library, qwen3-coder
Grux's catalogue lists Qwen 3 Coder 30b with its disk size and its larger memory estimateCookbook.swift

Questions

What is the best local LLM for coding on a 16 GB Mac?
Qwen 2.5 Coder 7b, a 4.7GB download, fits a 16 GB Mac with room for context. The 14b is too large for comfort at that size.
Can a MacBook run Qwen 3 Coder?
The 30b model runs on a Mac with about 48 GB of memory or more: Tight at 48 GB, a good fit from 64 GB. Smaller Macs should use a Qwen 2.5 Coder size that fits.
Is a local coding model private?
Yes. Run through Ollama, the model and your code stay on your Mac.
Download Grux AI 3.3.1 Read the source

Free, MIT licensed. macOS 14 or later, Apple silicon. 29.1 MB, signed and notarized by Apple. No account, no server, no subscription.