Model reference · open weights
mxbai-embed-xsmall is an open-weight embedding model from mixedbread-ai, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
mixedbread-ai/mxbai-embed-xsmall-v1 This model is an open-source English embedding model developed by Mixedbread. It's built upon sentence-transformers/all-MiniLM-L6-v2 and trained with the AnglE loss and Espresso. Read more details in our blog post. In a bread loaf: - State-of-the-art performance - Supports both binary quantization and Matryoshka Representation Learning (MRL). - Optimized for retrieval tasks - 4096 context support Performance Binary Quantization and Matryoshka Our model supports both binary quantization and Matryoshka Representation Learning (MRL), allowing for significant efficiency gains: - Binary quantization: Retains 93.9% of performance while increasing efficiency by a factor of 32 - MRL: A 33% reduction in vector size still leaves 96.2% of model performance These optimizations can lead to substantial reductions in infrastructure costs for cloud computing and vector databases. Read more here. Quickstart Here are several ways to produce German sentence embeddings using our model. Community Join our discord community to share your feedback and thoughts. We're here to help and always happy to discuss the exciting field of machine learning! License Apache 2.0 Citation
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | mixedbread-ai |
|---|---|
| Type | Embedding models |
| Parameters (lead) | 24M |
| Context | 4k tokens |
| Variants | 1 |
| Runs with | sentence-transformers |
| Based on | mixedbread-ai/mxbai-embed-mini-v1 |
| Released | 2024-09-13 |
| Popularity | 20k downloads / month |
| Likes | 37 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| mxbai-embed-xsmall-v1 | 24M | BF16 | ~0.1 GB | ✓ | Weights ↗ |
Benchmarks
As published on the model card — the maker's own numbers, not measured by AxForge.
| Task | Dataset | Metric | Score |
|---|---|---|---|
| Retrieval | MTEB ArguAna | ndcg_at_1 | 25.18 |
| Retrieval | MTEB ArguAna | ndcg_at_3 | 39.22 |
| Retrieval | MTEB ArguAna | ndcg_at_5 | 43.93 |
| Retrieval | MTEB ArguAna | ndcg_at_10 | 49.58 |
| Retrieval | MTEB ArguAna | ndcg_at_30 | 53.41 |
| Retrieval | MTEB ArguAna | ndcg_at_100 | 54.11 |
| Retrieval | MTEB ArguAna | map_at_1 | 25.18 |
| Retrieval | MTEB ArguAna | map_at_3 | 35.66 |
| Retrieval | MTEB ArguAna | map_at_5 | 38.25 |
| Retrieval | MTEB ArguAna | map_at_10 | 40.58 |
| Retrieval | MTEB ArguAna | map_at_30 | 41.6 |
| Retrieval | MTEB ArguAna | map_at_100 | 41.69 |
| Retrieval | MTEB ArguAna | recall_at_1 | 25.18 |
| Retrieval | MTEB ArguAna | recall_at_3 | 49.57 |
| Retrieval | MTEB ArguAna | recall_at_5 | 61.09 |
| Retrieval | MTEB ArguAna | recall_at_10 | 78.59 |
| Retrieval | MTEB ArguAna | recall_at_30 | 94.03 |
| Retrieval | MTEB ArguAna | recall_at_100 | 97.94 |
| Retrieval | MTEB ArguAna | precision_at_1 | 25.18 |
| Retrieval | MTEB ArguAna | precision_at_3 | 16.52 |
| Retrieval | MTEB ArguAna | precision_at_5 | 12.22 |
| Retrieval | MTEB ArguAna | precision_at_10 | 7.86 |
| Retrieval | MTEB ArguAna | precision_at_30 | 3.13 |
| Retrieval | MTEB ArguAna | precision_at_100 | 0.98 |
Using it via the API
Once AxForge deploys mxbai-embed-xsmall for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (mxbai-embed-xsmall below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/embeddings \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"mxbai-embed-xsmall","input":"text to embed"}'
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗
Explore