DavidAU · First MLX build 28 Jun 2025
Qwen3-18B-A3B-Stranger-Thoughts
MLX
Text apache-2.0
A 17B parameter text generation model from DavidAU, with 2 MLX builds, from 6-bit to 8-bit.
- Parameters
- 17B From Hugging Face
- Quantisation
- 6-bit Qwen3-18B-A3B-Stranger-Thoughts-Q_6
- Memory needed
- 18 GB Estimate, unified memory
- Download
- 14.1 GB Weights, estimated
- Downloads
- 69 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 2 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 18 GB at 6-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/Qwen3-18B-A3B-Stranger-Thoughts-Q_6 --prompt "Hello"MLX builds
2 on mlx-community| Qwen3-18B-A3B-Stranger-Thoughts-Q_6 | 6-bit | 14.1 GB | 18 GB | 69 |
|---|---|---|---|---|
| Qwen3-18B-A3B-Stranger-Thoughts-Q_8 | 8-bit | 18.4 GB | 23 GB | 41 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.