BG

bge m3

BGEGGUF by lm-kitUpdated 2024-11-06
Download on Hugging Face
Parameters567M
Context8K
Layers24
Architecturebert
Smallest quant0.4 GB
Quick answer

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 11 quants, from 0.4 GB (Q2_K) to 1.2 GB (F16).

bge m3 – a 0.567B BERT embedding model in GGUF format

bge m3 is a 0.567 billion‑parameter BERT model optimized for embedding tasks. It supports up to 8192 context tokens and is released under the MIT license. The model is available in multiple quantizations for efficient inference.

Good at

  • Fast embeddings for semantic search
  • Low‑memory inference with Q2_K
  • Large context support up to 8192 tokens

Limits

  • No generation capability
  • No vision support
  • Requires at least 1.7 GB VRAM for Q2_K at 8k context

Best for

  • Semantic search pipelines
  • Embedding‑based recommendation systems
  • Vector‑search indexing

Who it’s for. Developers building search or recommendation systems that need lightweight embeddings. Researchers requiring a small, fast BERT model for similarity tasks.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.4 GB 1.7 GB
Fits Get file →
Q3_K_S0.4 GB 1.7 GB
Fits Get file →
Q3_K_M0.4 GB 1.7 GB
Fits Get file →
Q3_K_L0.4 GB 1.7 GB
Fits Get file →
Q4_K_S0.4 GB 1.7 GB
Fits Get file →
Q4_K_M0.4 GB 1.7 GB
Fits Get file →
Q5_K_S0.5 GB 1.8 GB
Fits Get file →
Q5_K_M0.5 GB 1.8 GB
Fits Get file →
Q6_K0.5 GB 1.8 GB
Fits Get file →
Q8_00.6 GB 1.9 GB
Fits Get file →
F161.2 GB 2.5 GB
Fits Get file →

For 8 GB VRAM, Q2_K (0.37 GB) or Q3_K_S (0.38 GB) are suitable, using about 1.7 GB memory at 8k context. If more precision is needed and 12 GB VRAM is available, Q5_K_M (0.47 GB) or Q6_K (0.5 GB) can be used. The full F16 (1.16 GB) offers the highest quality but needs 2.5 GB memory.

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 F16 (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

Architecturebert
Parameters567M
Layers24
Trained context8,192 tokens
KV cache (fp16)96 KB per token

Source

Quantized bylm-kit
FamilyBGE
Licensemit
Downloads (HF)8,873
Last updated2024-11-06

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 F16: 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_S is 0.4 GB, Q3_K_M is 0.4 GB, Q3_K_L is 0.4 GB, Q4_K_S is 0.4 GB, Q4_K_M is 0.4 GB and 5 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 lm-kit/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, the Q2_K or Q3_K_S quantizations use about 1.7 GB memory at 8k context, fitting comfortably on 8 GB VRAM.

Does bge m3 support image inputs?

No, the model is purely text embedding and does not process visual data.

Is the model licensed for commercial use?

Yes, it is released under the MIT license, allowing commercial deployment.

Similar models

Browse all →

More from lm-kit

All by lm-kit →

More BGE models

All BGE →

Other tiny models

All tiny models →