JI

jina embeddings v4 text matching

JinaGGUF by jinaaiUpdated 2025-09-18
Download on Hugging Face
Parameters3.1B
Context125K
Layers36
Architectureqwen2vl
Smallest quant0.8 GB
Quick answer

jina embeddings v4 text matching needs about 2.7 GB of memory at Q4_K_M (a 1.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 18 quants, from 0.8 GB (IQ1_S) to 6.2 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.2 GB.

Jina Embeddings v4 text matching – multimodal, multilingual embedding model

Jina Embeddings v4 text matching is a GGUF model based on Qwen2.5-VL-3B-Instruct. It provides dense embeddings for text retrieval tasks. The model supports 2048‑dimensional vectors and can be truncated to 128 dimensions.

Good at

  • Dense text embeddings
  • Multilingual retrieval
  • Task‑specific adapters

Limits

  • No image input in this version
  • No multi‑vector output
  • License not specified

Best for

  • Sentence similarity searches
  • Document retrieval pipelines
  • Embedding generation for search engines

Who it’s for. Developers building retrieval systems that need multilingual text embeddings. The model is suitable for applications that require dense vector representations of text queries and passages.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S0.8 GB 1.6 GB
Fits Get file →
IQ1_M0.9 GB 1.7 GB
Fits Get file →
IQ2_XXS0.9 GB 1.8 GB
Fits Get file →
IQ2_M1.1 GB 1.9 GB
Fits Get file →
Q2_K1.3 GB 2.1 GB
Fits Get file →
IQ3_XXS1.3 GB 2.1 GB
Fits Get file →
IQ3_XS1.4 GB 2.2 GB
Fits Get file →
IQ3_S1.5 GB 2.3 GB
Fits Get file →
IQ3_M1.5 GB 2.3 GB
Fits Get file →
Q3_K_M1.6 GB 2.4 GB
Fits Get file →
IQ4_XS1.7 GB 2.5 GB
Fits Get file →
IQ4_NL1.8 GB 2.6 GB
Fits Get file →
Q4_K_M1.9 GB 2.7 GB
Fits Get file →
Q5_K_S2.2 GB 3.0 GB
Fits Get file →
Q5_K_M2.2 GB 3.0 GB
Fits Get file →
Q6_K2.5 GB 3.3 GB
Fits Get file →
Q8_03.3 GB 4.1 GB
Fits Get file →
F166.2 GB 7.0 GB
Fits Get file →

For 8 GB VRAM, use IQ1_S (0.79 GB) or IQ1_M (0.85 GB). For 16 GB VRAM, Q4_K_M (1.93 GB) or Q5_K_S (2.17 GB) are good choices. Larger models like Q8_0 (3.29 GB) need 32 GB VRAM or more.

What GPU do you need for jina embeddings v4 text matching?

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 Q6_K (2.5 GB file, about 3.3 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.3 GB file, about 4.1 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (6.2 GB file, about 7.0 GB in use).

Which jina embeddings v4 text matching quant should you choose?

Q4_K_M is the usual starting point for jina embeddings v4 text matching: it balances file size and quality well. Here it is a 1.9 GB file.

The Q8_0 file is 3.3 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 IQ1_S at 0.8 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

Architectureqwen2vl
Parameters3.1B
Layers36
Trained context128,000 tokens
KV cache (fp16)36 KB per token

Source

Quantized byjinaai
FamilyJina
Downloads (HF)4,047
Last updated2025-09-18

Frequently asked questions about jina embeddings v4 text matching

How much VRAM does jina embeddings v4 text matching need?

About 2.7 GB at Q4_K_M with an 8K context window. That is the 1.9 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 jina embeddings v4 text matching on an 8 GB GPU?

Yes, with F16: the 6.2 GB file needs about 7.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of jina embeddings v4 text matching GGUF?

It depends on the quant: IQ1_S is 0.8 GB, IQ1_M is 0.9 GB, IQ2_XXS is 0.9 GB, IQ2_M is 1.1 GB, Q2_K is 1.3 GB, IQ3_XXS is 1.3 GB and 12 more.

What context length does jina embeddings v4 text matching support?

The GGUF header lists a trained context length of 128,000 tokens (125K). 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 jina embeddings v4 text matching GGUF?

The files are on Hugging Face in the jinaai/jina-embeddings-v4-text-matching-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run this model on 8 GB VRAM?

Yes, IQ1_S and IQ1_M quantizations fit within 8 GB VRAM with approximate memory usage of 1.6–1.7 GB at 8k context.

Does this model support image input?

No, the text‑matching variant does not handle image input.

What embedding size can I use?

Dense embeddings default to 2048 dimensions and can be truncated to 128 dimensions with minimal performance loss.

Other GGUFs of jina-embeddings-v4

Similar models

Browse all →

More from jinaai

All by jinaai →

More Jina models

All Jina →

Other tiny models

All tiny models →