InfiniAILab · First MLX build 7 Apr 2025
QwQ-0.5B
MLX
Text
A 494M parameter text generation model from InfiniAILab, with 4 MLX builds, from 4-bit to fp16.
- Parameters
- 494M From Hugging Face
- Quantisation
- 6-bit QwQ-0.5B-6bit
- Memory needed
- 3 GB Estimate, unified memory
- Download
- 401 MB Weights, estimated
- Downloads
- 32 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 3 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/QwQ-0.5B-6bit --prompt "Hello"MLX builds
4 on mlx-community| QwQ-0.5B-4bit | 4-bit | 278 MB | 3 GB | 27 |
|---|---|---|---|---|
| QwQ-0.5B-6bit | 6-bit | 401 MB | 3 GB | 32 |
| QwQ-0.5B-8bit | 8-bit | 525 MB | 3 GB | 17 |
| QwQ-0.5B-fp16 | fp16 | 988 MB | 4 GB | 16 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.