LCO Embedding Omni 3B needs about 2.9 GB of memory at Q4_K_M (a 2.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 8 quants, from 1.3 GB (IQ2_M) to 6.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.2 GB.
LCO Embedding Omni 3B – 3.4B multimodal embedding model
LCO Embedding Omni 3B is a 3.4B parameter model based on Qwen2vl. It produces 2048‑dimensional embeddings for text, image, audio, and video. The model is released under the Apache‑2.0 license and supports embedding and vision tasks.
Good at
- Text‑to‑image retrieval
- Audio embedding generation
- Video embedding extraction
Limits
- No generative chat capability
- Requires mmproj for multimodal use
- Large VRAM needed for high‑quality quantizations
Best for
- Embedding‑based search engines
- Multimodal similarity matching
- Content recommendation systems
Who it’s for. Developers building multimodal search or recommendation systems that need compact embeddings. Researchers working on representation learning for text, image, audio, and video.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_M | 1.3 GB | 2.1 GB | Fits | Get file → | |
| Q2_K | 1.4 GB | 2.2 GB | Fits | Get file → | |
| IQ3_XS | 1.5 GB | 2.3 GB | Fits | Get file → | |
| IQ3_M | 1.6 GB | 2.4 GB | Fits | Get file → | |
| IQ4_XS | 1.9 GB | 2.7 GB | Fits | Get file → | |
| Q4_K_M | 2.1 GB | 2.9 GB | Fits | Get file → | |
| Q8_0 | 3.6 GB | 4.4 GB | Fits | Get file → | |
| BF16 | 6.8 GB | 7.6 GB | Tight | Get file → |
For 8 GB VRAM, use IQ2_M (1.27 GB, 2.1 GB memory) or Q2_K (1.38 GB, 2.2 GB memory). If 12 GB VRAM is available, Q4_K_M (2.1 GB, 2.9 GB memory) offers better quality. Higher precision models like Q8_0 or BF16 require more than 16 GB VRAM.
What GPU do you need for LCO Embedding Omni 3B?
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 (2.1 GB file, about 2.9 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (3.6 GB file, about 4.4 GB in use).
- 8 GB VRAM: the best quant that fits is BF16 (6.8 GB file, about 7.6 GB in use).
Which LCO Embedding Omni 3B quant should you choose?
Q4_K_M is the usual starting point for LCO Embedding Omni 3B: it balances file size and quality well. Here it is a 2.1 GB file.
The Q8_0 file is 3.6 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.
If memory is tight, the smallest file is IQ2_M at 1.3 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 LCO Embedding Omni 3B
How much VRAM does LCO Embedding Omni 3B need?
About 2.9 GB at Q4_K_M with an 8K context window. That is the 2.1 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 LCO Embedding Omni 3B on an 8 GB GPU?
Yes, with BF16: the 6.8 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of LCO Embedding Omni 3B GGUF?
It depends on the quant: IQ2_M is 1.3 GB, Q2_K is 1.4 GB, IQ3_XS is 1.5 GB, IQ3_M is 1.6 GB, IQ4_XS is 1.9 GB, Q4_K_M is 2.1 GB and 2 more.
What context length does LCO Embedding Omni 3B support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.2 GB at 32K.
Where can I download LCO Embedding Omni 3B GGUF?
The files are on Hugging Face in the marksverdhei/LCO-Embedding-Omni-3B-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 LCO Embedding Omni 3B 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 LCO Embedding Omni 3B on 8 GB VRAM?
Yes, the IQ2_M or Q2_K quantizations fit within 8 GB VRAM with an estimated 2.1–2.2 GB memory usage at 8K context.
Does the model support text‑only embeddings?
Yes, for text‑only use one of the text GGUFs; multimodal use also requires the mmproj file.
What license applies to this model?
The model is released under the Apache‑2.0 license, allowing free use and modification.