MLX Community · First MLX build 4 Sept 2025
embeddinggemma-300m-qat-q4_0-unquantized
MLX
Text gemma
A 308M parameter sentence similarity model, with one MLX build at 4-bit.
- Parameters
- 308M From Hugging Face
- Quantisation
- 4-bit embeddinggemma-300m-qat-q4_0-unquantized-bf16
- Memory needed
- 3 GB Estimate, unified memory
- Download
- 615 MB Weights, estimated
- Downloads
- 117 This build, last 30 days
- Task
- Sentence similarity Text
- MLX builds
- 1 On mlx-community
- Devices
- Mac Apple silicon
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/embeddinggemma-300m-qat-q4_0-unquantized-bf16MLX builds
1 on mlx-community| embeddinggemma-300m-qat-q4_0-unquantized-bf16 | 4-bit | 615 MB | 3 GB | 117 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.