Memory at each precision
| Version | Weights | With context | Smallest Mac |
|---|---|---|---|
| 8-bit | 425 GB | 459 GB | more than any Mac |
| 6-bit | 325 GB | 351 GB | 512 GB |
| 4-bit | 225 GB | 243 GB | 512 GB |
| 3-bit lower quality | 175 GB | 189 GB | 256 GB |
| 2-bit lower quality | 125 GB | 135 GB | 192 GB |
On every Apple chip
The smallest memory size of each chip that runs Llama 4 Maverick 17B-128E Instruct, 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 | 39–70 |
| 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 | 27–47 |
| 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 Runs well | 68–121 |
| 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 Llama 4 Maverick 17B-128E Instruct, 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/Llama-4-Maverick-17B-128E-Instruct-4bitBuild: mlx-community/Llama-4-Maverick-17B-128E-Instruct-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 Llama 4 Maverick 17B-128E Instruct
| Made by | Meta |
|---|---|
| Parameters | 400B total · 17B active (mixture of experts) |
| Context | 1M tokens |
| Licence | Llama 4 Community License |
| Released | 2025-04 |
| Input | Text and images |
| Intelligence | 9.3 on the Artificial Analysis Intelligence Index |
| Weights | meta-llama/Llama-4-Maverick-17B-128E-Instruct |
Questions
- How much memory does Llama 4 Maverick 17B-128E Instruct need?
- About 225 GB of weights at 4-bit, plus room for the context: 243 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 Llama 4 Maverick 17B-128E Instruct on a Mac?
- Writing speed depends on memory bandwidth. The fastest Mac for it here is an M5 Ultra with 512 GB at about 39–70 tokens a second (6-bit). The smallest Mac that runs it, with 512 GB, manages about 39–70 on an M5 Ultra.
- Why does Llama 4 Maverick 17B-128E Instruct run faster than its size suggests?
- It is a mixture-of-experts model: it holds 400B parameters in memory but reads only 17B 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 Llama 4 Maverick 17B-128E Instruct well and links here.
[](https://mlx.app/run/llama-4-maverick)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.