bge 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 9 quants, from 0.4 GB (Q2_K) to 1.2 GB.
BGE-M3: 0.567B parameter embedding model for dense, multi-vector, and sparse retrieval
BGE-M3 is a 0.567 billion parameter BERT‑based embedding model. It supports up to 8192‑token contexts and offers dense, multi‑vector, and sparse retrieval capabilities. The model is released under the MIT license and supports over 100 languages.
Good at
- Dense retrieval with 8192‑token context
- Multi‑vector and sparse retrieval in a single model
- Supports 100+ languages
Limits
- Requires ~1.7 GB VRAM for Q4_K at 8k context
- No vision or generation capabilities
- MIT license limits commercial use without attribution
Best for
- Building hybrid retrieval pipelines
- Embedding generation for large document collections
- Cross‑lingual retrieval tasks
Who it’s for. Developers building retrieval‑augmented systems who need a single model for dense, multi‑vector, and sparse retrieval. The model is suitable for research and production environments that require multilingual support and large context handling.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.4 GB | 1.7 GB | Fits | Get file → | |
| Q3_K | 0.4 GB | 1.7 GB | Fits | Get file → | |
| Q4_0 | 0.4 GB | 1.7 GB | Fits | Get file → | |
| Q4_K_M | 0.4 GB | 1.7 GB | Fits | Get file → | |
| Q5_0 | 0.5 GB | 1.8 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 → | |
| — | 1.2 GB | 2.5 GB | Fits | Get file → |
For 8 GB VRAM, Q4_K or Q4_K_M (0.44 GB file) is recommended, using ~1.7 GB memory at 8k context. If memory is limited to 4 GB, Q2_K (0.37 GB) or Q3_K (0.40 GB) can be used with similar memory usage. Larger quants such as Q8_0 increase file size to 0.63 GB and memory to 1.9 GB.
What GPU do you need for bge 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 the main file (1.2 GB file, about 2.5 GB in use).
Which bge m3 quant should you choose?
Q4_K_M is the usual starting point for bge 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 1.4 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.
If memory is tight, the smallest file is Q2_K at 0.4 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about bge m3
How much VRAM does bge 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 bge m3 on an 8 GB GPU?
Yes, with the smaller files: the 1.2 GB file needs about 2.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of bge m3 GGUF?
It depends on the quant: Q2_K is 0.4 GB, Q3_K is 0.4 GB, Q4_0 is 0.4 GB, Q4_K_M is 0.4 GB, Q5_0 is 0.5 GB, Q5_K_M is 0.5 GB and 3 more.
What context length does bge 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 bge m3 GGUF?
The files are on Hugging Face in the gpustack/bge-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 bge m3 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 BGE-M3 on 8 GB VRAM?
Yes, Q4_K or Q4_K_M quants use about 1.7 GB VRAM at 8k context, fitting within 8 GB.
Does BGE-M3 support image inputs?
No, BGE-M3 is an embedding model and does not process vision data.