Memory at each precision
| Version | Weights | With context | Smallest Mac |
|---|---|---|---|
| 8-bit | 2.6 TB | 2.8 TB | more than any Mac |
| 6-bit | 2 TB | 2.1 TB | more than any Mac |
| 4-bit | 1.4 TB | 1.5 TB | more than any Mac |
| 3-bit lower quality | 1.1 TB | 1.1 TB | more than any Mac |
| 2-bit lower quality | 750 GB | 810 GB | more than any Mac |
On every Apple chip
The smallest memory size of each chip that runs Qwen3.8 2.4T A95B, 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 | no size fits | Too big | – |
| 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 | no size fits | Too big | – |
| 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
No single Mac holds it. Smaller models below run well, and the guide to Mac clusters covers spreading a model over several Macs.
Step by step: download and run LLMs on a Mac · how to use MLX Harness · MLX vs Ollama vs llama.cpp
About Qwen3.8 2.4T A95B
| Made by | Qwen (Alibaba) |
|---|---|
| Parameters | 2,400B total · 95B active (mixture of experts) |
| Context | 256K tokens |
| Licence | Qwen3.8-Max license (qwen3.8-max) |
| Released | 2026-08 |
| Input | Text |
| Intelligence | 39.9 on the Artificial Analysis Intelligence Index |
| Weights | Qwen/Qwen3.8-2.4T-A95B |
Questions
- How much memory does Qwen3.8 2.4T A95B need?
- About 1.4 TB of weights at 4-bit, plus room for the context: 1.5 TB in all. That is more than any Mac has today.
- Can any Mac run Qwen3.8 2.4T A95B?
- Not on its own: even at 2 bits it needs more memory than the largest Mac. Use a smaller model, or spread it over several Macs with a cluster runtime.
- Why does Qwen3.8 2.4T A95B run faster than its size suggests?
- It is a mixture-of-experts model: it holds 2,400B parameters in memory but reads only 95B 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 Qwen3.8 2.4T A95B well and links here.
[](https://mlx.app/run/qwen3.8-2.4t-a95b)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.