bge reranker base Q4 K M needs about 1.0 GB of memory at Q4_K_M (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU.
BGE Reranker Base Q4 K M – lightweight embedding reranker
This model is a quantized version of BAAI/bge-reranker-base. It provides dense embeddings for reranking tasks. The GGUF file is 0.22 GB and requires about 1 GB of VRAM at 8 k context.
Good at
- Embedding generation
- Reranking queries
- Cross‑encoder style ranking
Limits
- No vision support
- Context limited to 512 tokens
- MIT license only
Best for
- Search engine ranking
- Document retrieval pipelines
- Query expansion
Who it’s for. Developers building retrieval‑augmented systems who need a small, fast reranker. The model is suitable for edge deployments with limited GPU memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.2 GB | 0.7 GB | Fits | Get file → |
The Q4_K_M quantization yields a 0.22 GB file and needs roughly 1 GB VRAM at 8 k context. For 8 GB VRAM systems this is a good fit. No other quants are available in the file list.
What GPU do you need for bge reranker base Q4 K M?
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 Q4_K_M (0.2 GB file, about 1.0 GB in use).
Which bge reranker base Q4 K M quant should you choose?
Q4_K_M is the usual starting point for bge reranker base Q4 K M: it balances file size and quality well. Here it is a 0.2 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about bge reranker base Q4 K M
How much VRAM does bge reranker base Q4 K M need?
About 1.0 GB at Q4_K_M with an 8K context window. That is the 0.2 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 bge reranker base Q4 K M on an 8 GB GPU?
Yes, with Q4_K_M: the 0.2 GB file needs about 1.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of bge reranker base Q4 K M GGUF?
It depends on the quant: Q4_K_M is 0.2 GB.
What context length does bge reranker base Q4 K M support?
The GGUF header lists a trained context length of 512 tokens (512). The KV cache grows with the context you use: about 0.3 GB at 8K and 0.0 GB at 512.
Where can I download bge reranker base Q4 K M GGUF?
The files are on Hugging Face in the sabafallah/bge-reranker-base-Q4_K_M-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 bge reranker base Q4 K M use?
Hugging Face lists the license as mit. 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 GB VRAM at 8 k context, leaving ample memory for other processes.
Does this model support image embeddings?
No, it only provides text embeddings; visual capabilities are not included.
What license does it use?
The model is released under the MIT license.