FitMyLLM
Jina AI/Dense

JJina Embeddings v4

jina-embeddings-v4 is a universal embedding model for multimodal and multilingual retrieval. The model is specially designed for complex document retrieval, including visually rich documents with charts, tables, and illustrations.

embeddingvisionmultilingual
3.8B
Parameters
125K
Context length
1
Benchmarks
6
Quantizations
0
Architecture
Dense
Released
2025-06-24
Layers
36
KV Heads
2
Head Dim
128
Family
embedding

Quantization Options

Context length:
QuantBitsVRAM @ 16KQuality
Q4_K_M4.89
3.2 GB
2.8 + 0.4 KV
good
Q5_K_S5.57
3.6 GB
3.1 + 0.4 KV
good
Q5_K_M5.7
3.6 GB
3.2 + 0.4 KV
good
Q6_K6.56
4.0 GB
3.6 + 0.4 KV
excellent
Q8_08.5
4.9 GB
4.5 + 0.4 KV
lossless
FP1616
8.5 GB
8.1 + 0.4 KV
lossless

Select your GPU above to see speed estimates and compatibility for each quantization.

Deploying for a team or in production? Size GPUs, cost & scaling in Enterprise →
Ready to run this?Rent by the hour

Rent a GPU and run Jina Embeddings v4 now

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Benchmarks (1)

Run this model

Easiest way to get started·Beginners
Docs ↗
curl -fsSL https://ollama.com/install.sh | sh
$# Jina Embeddings v4 is not in Ollama's library, and we know no GGUF build of it

Search Hugging Face for a GGUF of it (https://huggingface.co/models?sort=trending&search=jina-embeddings-v4+GGUF), or use the vLLM tab with the original weights.

Setup guide
>_

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more
Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

NVIDIA Tesla C2050
3 GB VRAM • 144 GB/s
NVIDIA
NVIDIA Tesla M2050
3 GB VRAM • 148 GB/s
NVIDIA
NVIDIA Tesla S2050
3 GB VRAM • 148 GB/s
NVIDIA

Find the best GPU for Jina Embeddings v4

Build Hardware for Jina Embeddings v4
Spec sheet

Jina Embeddings v4 — 3.8B Dense.

Specifications
Parameters
3.8B
Architecture
Dense Transformer
Context Length
125K tokens
Capabilities
embedding, vision, multilingual
Release Date
2025-06-24
Provider
Jina AI
Family
embedding
VRAM requirements
QuantBPWVRAMQuality
Q4_K_M4.892.8 GB94%
Q5_K_S5.573.1 GB96%
Q5_K_M5.73.2 GB96%
Q6_K6.563.6 GB97%
Q8_08.54.5 GB100%
FP16168.1 GB100%
Benchmark scores
MTEB Retrieval56.1
Compatible GPUs
30 @ Q4_K_M