Memory at each precision
| Version | Weights | With context | Smallest Mac |
|---|---|---|---|
| 8-bit | 717 GB | 775 GB | more than any Mac |
| 6-bit | 548 GB | 592 GB | more than any Mac |
| 4-bit | 380 GB | 410 GB | more than any Mac |
| 3-bit lower quality | 295 GB | 319 GB | 512 GB |
| 2-bit lower quality | 211 GB | 228 GB | 512 GB |
On every Apple chip
The smallest memory size of each chip that runs Mistral Large 3 (675B), 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 | 3-bit Runs well | 30–54 |
| 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 | 3-bit Runs well | 21–37 |
| M3 Max | no size fits | Too big | – |
| M3 Pro | no size fits | Too big | – |
| M3 | no size fits | Too big | – |
| M2 Ultra | no size fits | Too big | – |
| 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 Mistral Large 3 (675B), 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/Mistral-Large-3-675B-Instruct-2512-mlx-4bitBuild: mlx-community/Mistral-Large-3-675B-Instruct-2512-mlx-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 Mistral Large 3 (675B)
| Made by | Mistral AI |
|---|---|
| Parameters | 675B total · 41B active (mixture of experts) |
| Context | 256K tokens |
| Licence | Apache-2.0 |
| Released | 2025-11 |
| Input | Text and images |
| Weights | mistralai/Mistral-Large-3-675B-Instruct-2512 |
Questions
- How much memory does Mistral Large 3 (675B) need?
- About 380 GB of weights at 4-bit, plus room for the context: 410 GB in all. That is more than any Mac has today.
- How fast is Mistral Large 3 (675B) on a Mac?
- Writing speed depends on memory bandwidth. The fastest Mac for it here is an M5 Ultra with 512 GB at about 30–54 tokens a second (3-bit). The smallest Mac that runs it, with 512 GB, manages about 30–54 on an M5 Ultra.
- Why does Mistral Large 3 (675B) run faster than its size suggests?
- It is a mixture-of-experts model: it holds 675B parameters in memory but reads only 41B 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 Mistral Large 3 (675B) well and links here.
[](https://mlx.app/run/mistral-large-3)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.