GT

Gte Multilingual Reranker Base

GteGGUF by gpustackUpdated 2025-01-14
Download on Hugging Face
Parameters306M
Context8K
Layers12
Architecturenew
Smallest quant0.2 GB
Quick answer

Gte Multilingual Reranker Base 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 9 quants, from 0.2 GB (Q2_K) to 0.6 GB.

Gte Multilingual Reranker Base – 306M multilingual embedding model

The Gte Multilingual Reranker Base is a 306M parameter encoder-only transformer designed for multilingual retrieval. It supports up to 8192 tokens and over 70 languages. The model is available in GGUF format with several quantizations.

Good at

  • Multilingual text reranking
  • Embedding generation
  • Long‑context support

Limits

  • No vision support
  • Requires llama.cpp v0.0.72+
  • License is apache-2.0

Best for

  • Search engine ranking
  • Document similarity search
  • Multilingual QA pipelines

Who it’s for. Developers building multilingual search or recommendation systems. Researchers needing a lightweight reranker for evaluation. Engineers deploying offline inference on GPUs with limited memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.2 GB 1.0 GB
Fits Get file →
Q3_K0.2 GB 1.0 GB
Fits Get file →
Q4_00.2 GB 1.0 GB
Fits Get file →
Q4_K_M0.2 GB 1.0 GB
Fits Get file →
Q5_00.2 GB 1.0 GB
Fits Get file →
Q5_K_M0.2 GB 1.0 GB
Fits Get file →
Q6_K0.3 GB 1.1 GB
Fits Get file →
Q8_00.3 GB 1.1 GB
Fits Get file →
—0.6 GB 1.4 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M or Q5_K_M (file size 0.24 GB, memory ~1 GB). For 4 GB VRAM, choose Q4_0 or Q5_0 (file size 0.23–0.24 GB, memory ~1 GB). Higher precision quants like Q6_K or Q8_0 increase memory to ~1.1 GB.

What GPU do you need for Gte Multilingual Reranker Base?

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 the main file (0.6 GB file, about 1.4 GB in use).

Which Gte Multilingual Reranker Base quant should you choose?

Q4_K_M is the usual starting point for Gte Multilingual Reranker Base: 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 Q2_K at 0.2 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

Architecturenew
Parameters306M
Layers12
Trained context8,192 tokens
KV cache (fp16)36 KB per token

Source

Quantized bygpustack
FamilyGte
Licenseapache-2.0
Downloads (HF)1,028
Last updated2025-01-14

Frequently asked questions about Gte Multilingual Reranker Base

How much VRAM does Gte Multilingual Reranker Base 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 Gte Multilingual Reranker Base on an 8 GB GPU?

Yes, with the smaller files: 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 Gte Multilingual Reranker Base GGUF?

It depends on the quant: Q2_K is 0.2 GB, Q3_K is 0.2 GB, Q4_0 is 0.2 GB, Q4_K_M is 0.2 GB, Q5_0 is 0.2 GB, Q5_K_M is 0.2 GB and 3 more.

What context length does Gte Multilingual Reranker Base support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.3 GB at 8K and 0.3 GB at 8K.

Where can I download Gte Multilingual Reranker Base GGUF?

The files are on Hugging Face in the gpustack/gte-multilingual-reranker-base-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 Gte Multilingual Reranker Base 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 4 GB VRAM?

Yes, using Q4_0 or Q5_0 quants which require about 1 GB of VRAM at 8192 context.

Does this model support vision tasks?

No, it only provides text embedding and reranking capabilities.

What license applies to the GGUF files?

The GGUF files are released under the apache-2.0 license.

Similar models

Browse all →

More from gpustack

All by gpustack →

More Gte models

All Gte →

Other tiny models

All tiny models →