MLX Community · First MLX build 25 Dec 2025
Qwen3-VL-Text-30B-A3B-Instruct
MLX
Text
A 31B parameter text generation model, with one MLX build at bf16.
- Parameters
- 31B From Hugging Face
- Quantisation
- bf16 Qwen3-VL-Text-30B-A3B-Instruct-bf16
- Memory needed
- 71 GB Estimate, unified memory
- Download
- 61.1 GB Weights, estimated
- Downloads
- 44 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 1 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 71 GB at bf16
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-VL-Text-30B-A3B-Instruct-bf16 --prompt "Hello"MLX builds
1 on mlx-community| Qwen3-VL-Text-30B-A3B-Instruct-bf16 | bf16 | 61.1 GB | 71 GB | 44 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.