baai bge reranker v2 m3 m3 needs about 1.7 GB of memory at Q4_K_M (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.4 GB (Q4_K_M) to 0.6 GB (Q8_0).
BGE-Reranker-v2-M3 M3: 0.568B parameter embedding model
This BGE family model offers 0.568B parameters for embedding tasks. It supports up to 8192 context tokens and is licensed under apache-2.0. The model is available in four GGUF quantizations.
Good at
- Embedding generation
- Semantic similarity ranking
- Text retrieval
Limits
- No vision support
- Limited to 8192 token context
- Requires at least 1.7GB VRAM for Q4_K_M
Best for
- Search engine ranking
- Document clustering
- Information retrieval pipelines
Who it’s for. Developers needing efficient embedding generation for large text corpora. Suitable for search, recommendation, and retrieval systems that require a lightweight, open‑licensed model.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.4 GB | 1.7 GB | Fits | Get file → | |
| Q5_K_M | 0.5 GB | 1.8 GB | Fits | Get file → | |
| Q6_K | 0.5 GB | 1.8 GB | Fits | Get file → | |
| Q8_0 | 0.6 GB | 1.9 GB | Fits | Get file → |
For 8GB VRAM, Q4_K_M (0.44GB, 1.7GB memory) is recommended. If more VRAM is available, Q5_K_M (0.47GB, 1.8GB) or Q6_K (0.5GB, 1.8GB) can be used. Q8_0 (0.64GB, 1.9GB) offers the highest precision but needs the most memory.
What GPU do you need for baai bge reranker v2 m3 m3?
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 Q8_0 (0.6 GB file, about 1.9 GB in use).
Which baai bge reranker v2 m3 m3 quant should you choose?
Q4_K_M is the usual starting point for baai bge reranker v2 m3 m3: it balances file size and quality well. Here it is a 0.4 GB file.
The Q8_0 file is 0.6 GB, about 1.5 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about baai bge reranker v2 m3 m3
How much VRAM does baai bge reranker v2 m3 m3 need?
About 1.7 GB at Q4_K_M with an 8K context window. That is the 0.4 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 baai bge reranker v2 m3 m3 on an 8 GB GPU?
Yes, with Q8_0: the 0.6 GB file needs about 1.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of baai bge reranker v2 m3 m3 GGUF?
It depends on the quant: Q4_K_M is 0.4 GB, Q5_K_M is 0.5 GB, Q6_K is 0.5 GB, Q8_0 is 0.6 GB.
What context length does baai bge reranker v2 m3 m3 support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.8 GB at 8K and 0.8 GB at 8K.
Where can I download baai bge reranker v2 m3 m3 GGUF?
The files are on Hugging Face in the cPilotGod/baai-bge-reranker-v2-m3-m3-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 baai bge reranker v2 m3 m3 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 8 GB VRAM?
Yes, the Q4_K_M quantization requires about 1.7GB VRAM, which fits within an 8GB budget.
Does this model support image inputs?
No, the model only supports text embeddings and has no vision capabilities.
What license does the model use?
The model is released under the apache-2.0 license.