embeddinggemma-2-oQ8e
This model was quantized using oQ (oMLX v0.7.1) mixed-precision quantization with Improved oQe Quantization (jundot/omlx#4385).
A mixed-precision MLX checkpoint of google/embeddinggemma-2, Google DeepMind's multimodal embedding model that maps text, images, video and audio into one 768-dimensional vector space. It includes the text encoder, the vision encoder and the audio encoder. oQ quantizes the text encoder; the vision and audio encoders stay in BF16.
oMLX serves text and image inputs through POST /v1/embeddings (jundot/omlx#4333) and does not load the audio encoder.
The effective average is 13.258 bits/weight for the complete checkpoint.
Quantization and Bit Distribution
oQ8e allocates bits by measured layer sensitivity, then rounds each group with an importance matrix (128 samples x 512 tokens) and a weighted least-squares refit of its scale and bias.
| Storage format | Logical weights | Share of total | Tensor storage | Effective bits/weight |
|---|---|---|---|---|
| Affine 8-bit, group 64 | 0.272B | 36.555% | 0.269 GiB | 8.50 |
| BF16 | 0.472B | 63.445% | 0.880 GiB | 16.00 |
| Total | 0.744B | 100% | 1.149 GiB | 13.258 |
Storage Breakdown
| Component | Logical weights | Storage |
|---|---|---|
| Text encoder | 0.272B | 0.289 GB / 0.269 GiB |
| Vision encoder | 0.167B | 0.335 GB / 0.312 GiB |
| Audio encoder | 0.305B | 0.610 GB / 0.568 GiB |
| Total | 0.744B | 1.234 GB / 1.149 GiB |
License
Apache-2.0, following the source model. See LICENSE.