MLX Community · First MLX build 5 Oct 2024
llava-interleave-qwen-0.5b
MLX
TextVision tongyi-qianwen-research
A 864M parameter vision and text model, with 4 MLX builds, from 4-bit to bf16.
- Parameters
- 864M From Hugging Face
- Quantisation
- 8-bit llava-interleave-qwen-0.5b-8bit
- Memory needed
- 4 GB Estimate, unified memory
- Download
- 1.3 GB Weights, estimated
- Downloads
- 35 This build, last 30 days
- Task
- Vision and text Text, Vision
- MLX builds
- 4 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 4 GB at 8-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-vlm$ pip install -U mlx-vlm
$ python -m mlx_vlm.generate --model mlx-community/llava-interleave-qwen-0.5b-8bit --image photo.jpg --prompt "Describe this image"MLX builds
4 on mlx-community| llava-interleave-qwen-0.5b-4bit | 4-bit | 1.1 GB | 4 GB | 30 |
|---|---|---|---|---|
| llava-interleave-qwen-0.5b-6bit | 6-bit | 1.2 GB | 4 GB | 25 |
| llava-interleave-qwen-0.5b-8bit | 8-bit | 1.3 GB | 4 GB | 35 |
| llava-interleave-qwen-0.5b-bf16 | bf16 | 1.7 GB | 4 GB | 17 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.