JI

jina embeddings v4 text code

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 code 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‑code model for multimodal retrieval

Jina Embeddings v4 text‑code is a 3.1B‑parameter model based on qwen2vl. It produces dense embeddings for text and code, with optional task‑specific adapters. The model is quantized for efficient inference via llama.cpp.

Good at

  • Text and code embeddings
  • Multilingual retrieval
  • Task‑specific adapters

Limits

  • No image input in text‑only variants
  • No multi‑vector output in text‑only variants
  • License not specified

Best for

  • Embedding generation for search engines
  • Code similarity matching
  • Multilingual document retrieval

Who it’s for. Developers building retrieval systems that need compact embeddings for text and code. Researchers requiring a lightweight, quantized model for inference on limited hardware.

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 IQ4_NL (1.83 GB, 2.6 GB memory). For 4 GB VRAM, IQ3_XS (1.39 GB, 2.2 GB memory) is suitable. If memory is abundant, Q8_0 (3.29 GB, 4.1 GB memory) offers higher precision.

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

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 code quant should you choose?

Q4_K_M is the usual starting point for jina embeddings v4 text code: 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)2,291
Last updated2025-09-18

Frequently asked questions about jina embeddings v4 text code

How much VRAM does jina embeddings v4 text code 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 code 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 code 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 code 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 code GGUF?

The files are on Hugging Face in the jinaai/jina-embeddings-v4-text-code-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 IQ3_XS on 4 GB VRAM?

Yes, IQ3_XS requires 1.39 GB file size and estimates 2.2 GB memory at 8k context, fitting within 4 GB VRAM.

Does the model support image input?

The text‑code variant does not handle image input; only the multimodal version does.

What is the context length?

The model was trained with 128000 context tokens.

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 →