Granite Embedding 278m Multilingual 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. This repository has 17 quants, from 0.2 GB (IQ3_M) to 0.6 GB (F16).
Granite Embedding 278m Multilingual – 278 M parameter multilingual embedding model
Granite Embedding 278m Multilingual is a 278 M parameter encoder-only model that generates 768‑dimensional embeddings. It supports 12 languages and is trained with contrastive finetuning and knowledge distillation. The model is released under Apache 2.0.
Good at
- Multilingual text embeddings
- Text similarity and retrieval
- Embedding generation for search
Limits
- Requires 512‑token context
- No vision or generation capabilities
- License is Apache 2.0
Best for
- Embedding‑based search engines
- Semantic similarity tasks
- Retrieval‑augmented applications
Who it’s for. Developers and data scientists needing high‑quality multilingual embeddings for search, similarity, or retrieval tasks. The model is suitable for integration with SentenceTransformer or HuggingFace Transformers.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_M | 0.2 GB | 0.7 GB | Fits | Get file → | |
| Q3_K_M | 0.2 GB | 0.7 GB | Fits | Get file → | |
| IQ4_XS | 0.2 GB | 0.7 GB | Fits | Get file → | |
| Q3_K_L | 0.2 GB | 0.7 GB | Fits | Get file → | |
| Q4_0 | 0.2 GB | 0.7 GB | Fits | Get file → | |
| IQ4_NL | 0.2 GB | 0.7 GB | Fits | Get file → | |
| Q4_K_S | 0.2 GB | 0.7 GB | Fits | Get file → | |
| Q4_K_M | 0.2 GB | 0.7 GB | Fits | Get file → | |
| Q5_K_S | 0.2 GB | 0.7 GB | Fits | Get file → | |
| Q5_K_M | 0.2 GB | 0.7 GB | Fits | Get file → | |
| Q6_K | 0.2 GB | 0.8 GB | Fits | Get file → | |
| Q3_K_XL | 0.3 GB | 0.8 GB | Fits | Get file → | |
| Q4_K_L | 0.3 GB | 0.8 GB | Fits | Get file → | |
| Q5_K_L | 0.3 GB | 0.8 GB | Fits | Get file → | |
| Q6_K_L | 0.3 GB | 0.8 GB | Fits | Get file → | |
| Q8_0 | 0.3 GB | 0.8 GB | Fits | Get file → | |
| F16 | 0.6 GB | 1.1 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (0.22 GB) or Q5_K_S (0.22 GB). For 4 GB VRAM, use IQ3_M (0.21 GB) or Q3_K_M (0.21 GB). Larger VRAM allows Q8_0 (0.30 GB) for higher precision. Memory estimates are approximate.
What GPU do you need for Granite Embedding 278m Multilingual?
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 (0.6 GB file, about 1.4 GB in use).
Which Granite Embedding 278m Multilingual quant should you choose?
Q4_K_M is the usual starting point for Granite Embedding 278m Multilingual: it balances file size and quality well. Here it is a 0.2 GB file.
The Q8_0 file is 0.3 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 IQ3_M at 0.2 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about Granite Embedding 278m Multilingual
How much VRAM does Granite Embedding 278m Multilingual 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 Granite Embedding 278m Multilingual on an 8 GB GPU?
Yes, with F16: the 0.6 GB file needs about 1.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Granite Embedding 278m Multilingual GGUF?
It depends on the quant: IQ3_M is 0.2 GB, Q3_K_M is 0.2 GB, IQ4_XS is 0.2 GB, Q3_K_L is 0.2 GB, Q4_0 is 0.2 GB, IQ4_NL is 0.2 GB and 11 more.
What context length does Granite Embedding 278m Multilingual 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 Granite Embedding 278m Multilingual GGUF?
The files are on Hugging Face in the bartowski/granite-embedding-278m-multilingual-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 Granite Embedding 278m Multilingual 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 this model on 8 GB VRAM?
Yes, use a quantization such as Q4_K_M or Q5_K_S which are 0.22 GB and require about 1 GB of VRAM at 8k context.
Does the model support image inputs?
No, the model only handles text embeddings and has no vision capability.
Is the model free to use?
Yes, it is licensed under Apache 2.0, which allows free use and modification.