Granite Embedding 107m Multilingual needs about 0.7 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 17 quants, from 0.1 GB (IQ3_M) to 0.2 GB (F16).
Granite Embedding 107m Multilingual – 107M parameter dense embedding model
Granite Embedding 107m Multilingual is a 107M parameter dense biencoder embedding model. It produces 384‑dimensional vectors for text similarity, retrieval, and search. The model is trained with contrastive finetuning and knowledge distillation.
Good at
- Text similarity and retrieval
- Multilingual embeddings for 12 supported languages
- Fast inference compared to similar models
Limits
- No vision support
- Context length limited to 512 tokens
- Requires Apache 2.0 license
Best for
- Embedding generation for search engines
- Similarity scoring in multilingual applications
- Retrieval augmentation in NLP pipelines
Who it’s for. Developers building search or recommendation systems that need multilingual embeddings. Researchers requiring a lightweight, 107M parameter model for embedding tasks.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_M | 0.1 GB | 0.6 GB | Fits | Get file → | |
| IQ4_XS | 0.1 GB | 0.6 GB | Fits | Get file → | |
| IQ4_NL | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q4_0 | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q3_K_M | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q3_K_L | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q3_K_XL | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q4_K_S | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q4_K_L | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q4_K_M | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q5_K_S | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q5_K_L | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q5_K_M | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q6_K | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q6_K_L | 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 → |
For 8 GB VRAM, use any quant with file size 0.12 GB such as IQ3_M, IQ4_XS, Q4_K_M, or Q6_K. All these quants estimate 0.7 GB memory at 8 k context. If you need higher precision, choose Q8_0 (0.12 GB) or F16 (0.22 GB) but expect 0.8 GB memory usage.
What GPU do you need for Granite Embedding 107m 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 (0.2 GB file, about 0.8 GB in use).
Which Granite Embedding 107m Multilingual quant should you choose?
Q4_K_M is the usual starting point for Granite Embedding 107m Multilingual: it balances file size and quality well. Here it is a 0.1 GB file.
The Q8_0 file is 0.1 GB, about 1.0 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 0.1 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 107m Multilingual
How much VRAM does Granite Embedding 107m Multilingual need?
About 0.7 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 Granite Embedding 107m Multilingual on an 8 GB GPU?
Yes, with F16: the 0.2 GB file needs about 0.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Granite Embedding 107m Multilingual GGUF?
It depends on the quant: IQ3_M is 0.1 GB, IQ4_XS is 0.1 GB, IQ4_NL is 0.1 GB, Q4_0 is 0.1 GB, Q3_K_M is 0.1 GB, Q3_K_L is 0.1 GB and 11 more.
What context length does Granite Embedding 107m Multilingual support?
The GGUF header lists a trained context length of 512 tokens (512). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.0 GB at 512.
Where can I download Granite Embedding 107m Multilingual GGUF?
The files are on Hugging Face in the bartowski/granite-embedding-107m-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 107m 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, any quant with file size 0.12 GB will use approximately 0.7 GB memory at 8 k context, fitting within 8 GB VRAM.
Does this model support image inputs?
No, the model is an embedding encoder and does not support vision inputs.
What license does the model use?
The model is released under the Apache 2.0 license.