Alibaba Qwen · First MLX build 2 Mar 2026 · In Core AI since 16 Oct 2026
Qwen3.5-0.8B
MLXCore AI
Text apache-2.0
A 873M parameter text classification model from Alibaba Qwen, with 5 MLX builds, from 4-bit to bf16 and Apple Core AI export recipes for macOS.
- Parameters
- 873M From Hugging Face
- Quantisation
- 4-bit Qwen3.5-0.8B-MLX-4bit
- Memory needed
- 3 GB Estimate, unified memory
- Download
- 625 MB Weights, estimated
- Downloads
- 4.0K This build, last 30 days
- Task
- Text classification Text
- MLX builds
- 5 On mlx-community
- Devices
- Mac Apple silicon
- Parameters
- 873M From Hugging Face
- Compression
- None Apple’s preset
- Memory needed
- — Parameter count not published
- Context
- 256K tokens Fixed at export
- Precision
- BF16 Compute precision
- Platforms
- macOS Mac
- Export presets
- 1 In Apple’s registry
- Listed by Apple
- 16 Oct 2026 First registry commit
Memory
Will it fit?Needs about 3 GB at 4-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 · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/Qwen3.5-0.8B-MLX-4bitMemory
There is no memory estimate: the parameter count for this model is not published on Hugging Face.
Export it
Terminal · uv$ git clone https://github.com/apple/coreai-models
$ cd coreai-models
$ uv run coreai.llm.export qwen3.5-0.8b
Apple publishes the recipe, not a ready-made package: these commands convert the original weights to a Core AI .aimodel on your Mac. See the repository for requirements.
MLX builds
5 on mlx-community| Qwen3.5-0.8B-OptiQ-4bit | 4-bit | 424 MB | 3 GB | 1.3K |
|---|---|---|---|---|
| Qwen3.5-0.8B-MLX-4bit | 4-bit | 625 MB | 3 GB | 4.0K |
| Qwen3.5-0.8B-MLX-8bit | 8-bit | 1.0 GB | 4 GB | 504 |
| Qwen3.5-0.8B-MLX-bf16 | bf16 | 1.7 GB | 4 GB | 192 |
| Qwen3.5-0.8B-decision | Unstated | 1.7 GB | 4 GB | 1.6K |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.
Core AI export presets
From Apple’s registry| Preset | Platform | Compression | Precision | Context |
|---|---|---|---|---|
| qwen3.5-0.8b | macOS | None | BF16 | 256K |