bge-base-en-v1.5 needs about 0.9 GB of memory at Q4_K_M (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.1 GB (Q4_K_M) to 0.4 GB (F32).
Compact BERT-based embedding model in GGUF format
bge-base-en-v1.5 is a 0.109‑billion‑parameter BERT model quantized for use with llama.cpp. It provides sentence embeddings and supports CPU and GPU inference with modest speedups. The model is licensed under MIT and has a 512‑token context window.
Good at
- Fast embedding generation
- Low memory footprint
- CPU‑friendly
Limits
- 512‑token context only
- No vision or generation capabilities
- Requires GGUF format
Best for
- Semantic search
- Text similarity tasks
- Embedding‑based clustering
Who it’s for. Developers needing lightweight sentence embeddings for search or clustering. Suitable for edge deployments and local inference with llama.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q8_0 | 0.1 GB | 0.6 GB | Fits | Get file → | |
| F16 | 0.2 GB | 0.7 GB | Fits | Get file → | |
| F32 | 0.4 GB | 1.0 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (0.07 GB) or Q8_0 (0.12 GB). For 4 GB VRAM, Q4_K_M is recommended. Higher precision F16 or F32 increases memory to 1–1.2 GB and is unnecessary for most use cases.
What GPU do you need for bge-base-en-v1.5?
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 (0.4 GB file, about 1.2 GB in use).
Which bge-base-en-v1.5 quant should you choose?
Q4_K_M is the usual starting point for bge-base-en-v1.5: it balances file size and quality well. Here it is a 0.1 GB file.
The Q8_0 file is 0.1 GB, about 1.7 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
Source
Frequently asked questions about bge-base-en-v1.5
How much VRAM does bge-base-en-v1.5 need?
About 0.9 GB at Q4_K_M 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 bge-base-en-v1.5 on an 8 GB GPU?
Yes, with F32: the 0.4 GB file needs about 1.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of bge-base-en-v1.5 GGUF?
It depends on the quant: Q4_K_M is 0.1 GB, Q8_0 is 0.1 GB, F16 is 0.2 GB, F32 is 0.4 GB.
What context length does bge-base-en-v1.5 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-base-en-v1.5 GGUF?
The files are on Hugging Face in the CompendiumLabs/bge-base-en-v1.5-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-base-en-v1.5 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-base-en-v1.5 on 4 GB VRAM?
Yes, the Q4_K_M quantized file is 0.07 GB and requires about 0.9 GB memory at 8k context.
Does this model support text generation?
No, it only provides embeddings and does not generate text.
Is the model multilingual?
The model is trained for English only; no other languages are supported.