mxbai embed xsmall v1 needs about 0.6 GB of memory at BF16 (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.0 GB (Q8_0) to 0.1 GB (F32).
Small, efficient English sentence embedding model
mxbai embed xsmall v1 is a 26 million‑parameter BERT‑based model for generating sentence embeddings. It supports 4096‑token context and is optimized for retrieval tasks. The model is released under Apache 2.0 and is available in several quantized GGUF formats.
Good at
- Fast inference on low‑memory GPUs
- High retrieval accuracy
- Compact embeddings
Limits
- No vision or multimodal support
- Requires 8 k context for full performance
- Only English language
Best for
- Embedding‑based search engines
- Semantic clustering
- Vector database indexing
Who it’s for. Developers building lightweight embedding pipelines or running embeddings on edge devices. The model is suitable for applications that need quick, small embeddings without heavy GPU resources.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 0.0 GB | 0.6 GB | Fits | Get file → | |
| BF16 | 0.1 GB | 0.6 GB | Fits | Get file → | |
| F16 | 0.1 GB | 0.6 GB | Fits | Get file → | |
| F32 | 0.1 GB | 0.6 GB | Fits | Get file → |
For 8 GB VRAM, use Q8_0 (0.03 GB file, ~0.6 GB RAM). If you need even less memory, BF16 or F16 (0.05 GB) are also suitable. F32 (0.1 GB) offers full precision but uses more memory.
What GPU do you need for mxbai embed xsmall v1?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is F32 (0.1 GB file, about 0.7 GB in use).
Which mxbai embed xsmall v1 quant should you choose?
BF16 (0.1 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
If memory is tight, the smallest file is Q8_0 at 0.0 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about mxbai embed xsmall v1
How much VRAM does mxbai embed xsmall v1 need?
About 0.6 GB at BF16 with an 8K context window. That is the 0.1 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run mxbai embed xsmall v1 on an 8 GB GPU?
Yes, with F32: the 0.1 GB file needs about 0.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of mxbai embed xsmall v1 GGUF?
It depends on the quant: Q8_0 is 0.0 GB, BF16 is 0.1 GB, F16 is 0.1 GB, F32 is 0.1 GB.
What context length does mxbai embed xsmall v1 support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.0 GB at 4K.
Where can I download mxbai embed xsmall v1 GGUF?
The files are on Hugging Face in the mixedbread-ai/mxbai-embed-xsmall-v1 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does mxbai embed xsmall v1 use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run this model on 4 GB VRAM?
Yes, the Q8_0 quantized file is only 0.03 GB and requires about 0.6 GB of RAM at 8 k context.
Does it support multilingual embeddings?
No, the model is trained only for English embeddings.
Is there a vision component?
No, the model is purely text embedding and has no vision support.