mxbai rerank xsmall v1 needs about 0.7 GB of memory at Q4_K (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.1 GB (IQ4_XS) to 0.3 GB.
Fast cross‑encoder reranker for English
mxbai‑rerank‑xsmall‑v1 is a lightweight BERT‑based reranker with 0.0708 billion parameters. It is designed for quick reranking of search results and works well with keyword search. The model is released under Apache‑2.0.
Good at
- Efficient reranking
- Low memory footprint
- Fast inference with ggml
Limits
- No vision support
- Small context window of 512 tokens
- Requires Apache‑2.0 license
Best for
- Search engine reranking
- Document relevance scoring
- Embedding generation for retrieval
Who it’s for. Developers building search or retrieval systems that need a fast, small reranker. The model is suitable for edge deployments and low‑resource environments.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ4_XS | 0.1 GB | 0.6 GB | Fits | Get file → | |
| IQ4_XS | 0.1 GB | 0.6 GB | Fits | Get file → | |
| IQ4_XS | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q4_K | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q4_K | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q4_K | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q4_K | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q4_K | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q8_0 | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q8_0 | 0.1 GB | 0.6 GB | Fits | Get file → | |
| — | 0.2 GB | 0.8 GB | Fits | Get file → | |
| — | 0.3 GB | 0.8 GB | Fits | Get file → |
For 8 GB VRAM, use IQ4_XS or Q4_K files (0.07 GB each, ~0.7 GB RAM at 8 k context). If more memory is available, Q8_0 (0.08 GB) offers higher precision. The estimates are approximate.
What GPU do you need for mxbai rerank 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 the main file (0.3 GB file, about 0.9 GB in use).
Which mxbai rerank xsmall v1 quant should you choose?
Q4_K (0.1 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is IQ4_XS at 0.1 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about mxbai rerank xsmall v1
How much VRAM does mxbai rerank xsmall v1 need?
About 0.7 GB at Q4_K 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 rerank xsmall v1 on an 8 GB GPU?
Yes, with the smaller files: the 0.3 GB file needs about 0.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of mxbai rerank xsmall v1 GGUF?
It depends on the quant: IQ4_XS is 0.1 GB, IQ4_XS is 0.1 GB, IQ4_XS is 0.1 GB, Q4_K is 0.1 GB, Q4_K is 0.1 GB, Q4_K is 0.1 GB and 6 more.
What context length does mxbai rerank xsmall v1 support?
The GGUF header lists a trained context length of 512 tokens (512). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.0 GB at 512.
Where can I download mxbai rerank xsmall v1 GGUF?
The files are on Hugging Face in the cstr/mxbai-rerank-xsmall-v1-GGUF 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 rerank 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 IQ4_XS and Q4_K variants use about 0.7 GB of RAM at 8 k context, fitting within 4 GB VRAM with headroom.
Does it support multilingual text?
No, the model is trained for English only.
Is there a vision capability?
No, the model does not support vision inputs.