Google · First MLX build 6 Oct 2026 · In Core AI since 5 Nov 2026
embeddinggemma-2
MLXCore AI
Text apache-2.0
A 744M parameter embeddings model from Google, with 8 MLX builds, from 4-bit to bf16 and Apple Core AI export recipes for iOS, macOS.
- Parameters
- 744M From Hugging Face
- Quantisation
- 8-bit embeddinggemma-2-8bit
- Memory needed
- 4 GB Estimate, unified memory
- Download
- 1.2 GB Weights, estimated
- Downloads
- 5.7K This build, last 30 days
- Task
- Embeddings Text
- MLX builds
- 8 On mlx-community
- Devices
- Mac Apple silicon
- Parameters
- 744M From Hugging Face
- Compression
- — Apple’s preset
- Memory needed
- — Parameter count not published
- Context
- — Fixed at export
- Precision
- — Compute precision
- Platforms
- iOS, macOS Not stated
- Export presets
- 1 In Apple’s registry
- Listed by Apple
- 5 Nov 2026 First registry commit
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 · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/embeddinggemma-2-8bitMemory
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.embedding.export embeddinggemma-2
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
8 on mlx-community| embeddinggemma-2-4bit | 4-bit | 1.1 GB | 4 GB | 892 |
|---|---|---|---|---|
| embeddinggemma-2-nvfp4 | 4-bit | 1.1 GB | 4 GB | 367 |
| embeddinggemma-2-mxfp4 | MXFP4 | 1.1 GB | 4 GB | 339 |
| embeddinggemma-2-5bit | 5-bit | 1.1 GB | 4 GB | 344 |
| embeddinggemma-2-6bit | 6-bit | 1.2 GB | 4 GB | 320 |
| embeddinggemma-2-8bit | 8-bit | 1.2 GB | 4 GB | 5.7K |
| embeddinggemma-2-mxfp8 | MXFP8 | 1.2 GB | 4 GB | 737 |
| embeddinggemma-2-bf16 | bf16 | 1.5 GB | 4 GB | 5.3K |
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 |
|---|---|---|---|---|
| embeddinggemma-2 | iOS, macOS | — | — | — |