Alibaba Qwen · In Core AI since 8 Jun 2026
Qwen2.5-1.5B-Instruct
Core AI
Text apache-2.0
A 1.5B parameter text generation model from Alibaba Qwen, with Apple Core AI export recipes for macOS and iOS.
- Parameters
- 1.5B From Hugging Face
- Compression
- 4-bit, 4-bit weights, 8-bit KV cache, 4-bit weight palettized group8 Apple’s preset
- Memory needed
- 3 GB Estimate from parameters
- Context
- 32K tokens Fixed at export
- Precision
- FP16 Compute precision
- Platforms
- macOS, iOS Mac and iPhone
- Export presets
- 3 In Apple’s registry
- Listed by Apple
- 8 Jun 2026 First registry commit
Memory
Will it fit?Needs about 3 GB at 4-bit, 4-bit weights, 8-bit KV cache, 4-bit weight palettized group8
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the parameter count at Apple’s compression setting. Apple does not publish package sizes.
Export it
Terminal · uv$ git clone https://github.com/apple/coreai-models
$ cd coreai-models
$ uv run coreai.llm.export qwen2.5-1.5b-instruct
$ uv run coreai.llm.export qwen2.5-1.5b-instruct-8bit-kv
$ uv run coreai.llm.export qwen2.5-1.5b-instruct --platform iOS
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.
Core AI export presets
From Apple’s registry| Preset | Platform | Compression | Precision | Context |
|---|---|---|---|---|
| qwen2.5-1.5b-instruct | macOS | 4-bit | FP16 | 32K |
| qwen2.5-1.5b-instruct-8bit-kv INT4 per-block weights and INT8 per-tensor KV cache. |
macOS | 4-bit weights, 8-bit KV cache | FP16 | 32K |
| qwen2.5-1.5b-instruct | iOS | 4-bit weight palettized group8 | FP16 | 4K |