kalomaze · First MLX build 3 May 2025
Qwen3-16B-A3B
MLX
Text apache-2.0
A 16B parameter text generation model from kalomaze, with one MLX build at bf16.
- Parameters
- 16B From Hugging Face
- Quantisation
- bf16 Qwen3-16B-A3B-bf16
- Memory needed
- 38 GB Estimate, unified memory
- Download
- 32.1 GB Weights, estimated
- Downloads
- 53 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 38 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/Qwen3-16B-A3B-bf16 --prompt "Hello"MLX builds
1 on mlx-community| Qwen3-16B-A3B-bf16 | bf16 | 32.1 GB | 38 GB | 53 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.