Alibaba Qwen · First MLX build 12 Sept 2025
Qwen3-Next-80B-A3B-Instruct
MLX
Text apache-2.0
A 80B parameter text generation model from Alibaba Qwen, with 4 MLX builds, from 4-bit to 8-bit.
- Parameters
- 80B From Hugging Face
- Quantisation
- 4-bit Qwen3-Next-80B-A3B-Instruct-4bit
- Memory needed
- 53 GB Estimate, unified memory
- Download
- 44.8 GB Weights, estimated
- Downloads
- 1.5K This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 4 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 53 GB at 4-bit
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · mlx-lm$ pip install -U mlx-lm
$ mlx_lm.generate --model mlx-community/Qwen3-Next-80B-A3B-Instruct-4bit --prompt "Hello"MLX builds
4 on mlx-community| Qwen3-Next-80B-A3B-Instruct-4bit | 4-bit | 44.8 GB | 53 GB | 1.5K |
|---|---|---|---|---|
| Qwen3-Next-80B-A3B-Instruct-5bit | 5-bit | 54.8 GB | 64 GB | 79 |
| Qwen3-Next-80B-A3B-Instruct-6bit | 6-bit | 64.7 GB | 75 GB | 81 |
| Qwen3-Next-80B-A3B-Instruct-8bit | 8-bit | 84.7 GB | 97 GB | 666 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.