Alibaba Qwen · First MLX build 3 Feb 2026
Qwen3-Coder-Next
MLX
Text apache-2.0
A 80B parameter text generation model from Alibaba Qwen, with 8 MLX builds, from 4-bit to bf16.
- Parameters
- 80B From Hugging Face
- Quantisation
- 4-bit Qwen3-Coder-Next-4bit
- Memory needed
- 53 GB Estimate, unified memory
- Download
- 44.8 GB Weights, estimated
- Downloads
- 4.6K This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 8 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-Coder-Next-4bit --prompt "Hello"MLX builds
8 on mlx-community| Qwen3-Coder-Next-4bit | 4-bit | 44.8 GB | 53 GB | 4.6K |
|---|---|---|---|---|
| Qwen3-Coder-Next-mxfp4 | MXFP4 | 44.8 GB | 53 GB | 184 |
| Qwen3-Coder-Next-nvfp4 | 4-bit | 44.8 GB | 53 GB | 117 |
| Qwen3-Coder-Next-5bit | 5-bit | 54.8 GB | 64 GB | 505 |
| Qwen3-Coder-Next-6bit | 6-bit | 64.7 GB | 75 GB | 1.8K |
| Qwen3-Coder-Next-8bit | 8-bit | 84.7 GB | 97 GB | 2.7K |
| Qwen3-Coder-Next-mxfp8 | MXFP8 | 84.7 GB | 97 GB | 153 |
| Qwen3-Coder-Next-bf16 | bf16 | 159 GB | 181 GB | 412 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.