Memory at each precision
| Version | Weights | With context | Smallest Mac |
|---|---|---|---|
| 8-bit | 455 GB | 491 GB | more than any Mac |
| 6-bit | 348 GB | 376 GB | 512 GB |
| 4-bit | 241 GB | 260 GB | 512 GB |
| 3-bit lower quality | 187 GB | 202 GB | 512 GB |
| 2-bit lower quality | 134 GB | 145 GB | 256 GB |
On every Apple chip
The smallest memory size of each chip that runs MiniMax M3, the best version that fits it, and the writing speed you can expect.
| Chip | Needs | Version | Tokens/s |
|---|---|---|---|
| M6 | no size fits | Too big | – |
| M5 Ultra | 512 GB | 6-bit Runs well | 29–51 |
| M5 Max | no size fits | Too big | – |
| M5 Pro | no size fits | Too big | – |
| M5 | no size fits | Too big | – |
| M4 Max | no size fits | Too big | – |
| M4 Pro | no size fits | Too big | – |
| M4 | no size fits | Too big | – |
| M3 Ultra | 512 GB | 6-bit Runs well | 20–35 |
| M3 Max | no size fits | Too big | – |
| M3 Pro | no size fits | Too big | – |
| M3 | no size fits | Too big | – |
| M2 Ultra | 192 GB | 2-bit Only just | 50–89 |
| M2 Max | no size fits | Too big | – |
| M2 Pro | no size fits | Too big | – |
| M2 | no size fits | Too big | – |
| M1 Ultra | no size fits | Too big | – |
| M1 Max | no size fits | Too big | – |
| M1 Pro | no size fits | Too big | – |
| M1 | no size fits | Too big | – |
How to run it
- The easy way: download MLX Harness, free and open source. Search for MiniMax M3, download the version that fits your Mac, and chat. It also serves the model to your other apps over an OpenAI-compatible API.Download MLX HarnessFree · Apple Silicon · macOS 14.5 or later
- In Terminal with Apple’s MLX:
pip install mlx-lmmlx_lm.chat --model mlx-community/MiniMax-M3-4bitBuild: mlx-community/MiniMax-M3-4bit on Hugging Face. Other precisions sit next to it.
Step by step: download and run LLMs on a Mac · how to use MLX Harness · MLX vs Ollama vs llama.cpp
About MiniMax M3
| Made by | MiniMax |
|---|---|
| Parameters | 428B total · 23B active (mixture of experts) |
| Context | 1M tokens |
| Licence | MiniMax Community License (custom) |
| Released | 2026-06 |
| Input | Text and images |
| Intelligence | 29.2 on the Artificial Analysis Intelligence Index |
| Weights | MiniMaxAI/MiniMax-M3 |
Questions
- How much memory does MiniMax M3 need?
- About 241 GB of weights at 4-bit, plus room for the context: 260 GB in all. On a Mac that means 512 GB of unified memory or more, since macOS lets the GPU use about 75% of it by default.
- How fast is MiniMax M3 on a Mac?
- Writing speed depends on memory bandwidth. The fastest Mac for it here is an M5 Ultra with 512 GB at about 29–51 tokens a second (6-bit). The smallest Mac that runs it, with 512 GB, manages about 29–51 on an M5 Ultra.
- Why does MiniMax M3 run faster than its size suggests?
- It is a mixture-of-experts model: it holds 428B parameters in memory but reads only 23B for each token, so it writes at the speed of a much smaller model.
Similar models
For your model card or README
Shows the smallest Mac that runs MiniMax M3 well and links here.
[](https://mlx.app/run/minimax-m3)How it’s worked out
Memory: the model’s parameters at 8, 6, 4, 3 or 2 bits per weight plus MLX’s group scales (half a bit per weight), or its native format, with room for the context on top. By default macOS lets the GPU use about 75% of unified memory. Speed: memory bandwidth divided by the bytes read per token is the ceiling for one conversation; in llama.cpp’s public Apple Silicon benchmarks real runs reach about 45% to 80% of it, which is the range shown. These are estimates, not measurements: measure your own Mac on MLX Bench. Model figures from each official model card, chip figures from Apple’s Tech Specs. Checked 2026-10-19. Same data as mlx.app/compare.