Jina Embeddings v4 Vllm Retrieval 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 25 quants, from 0.0 GB to 2.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.2 GB.
Jina Embeddings v4 Vllm Retrieval – multimodal embedding model
Jina Embeddings v4 Vllm Retrieval is a 3.1B parameter model based on Qwen2VL. It is optimized for embedding generation and retrieval tasks. The model is available in multiple GGUF quantizations.
Good at
- Embedding generation
- Multimodal retrieval
- Low‑latency inference
Limits
- No vision support in this GGUF release
- License is cc‑by‑nc‑4.0
- Requires 8k context for estimates
Best for
- Embedding search engines
- Vector database indexing
- Semantic similarity tasks
Who it’s for. Developers building retrieval systems that need fast, low‑memory embeddings. Researchers requiring a multimodal embedding model with a permissive non‑commercial license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.8 GB | Fits | Get file → | |
| IQ1_S | 0.8 GB | 1.6 GB | Fits | Get file → | |
| IQ1_M | 0.9 GB | 1.7 GB | Fits | Get file → | |
| IQ2_XXS | 0.9 GB | 1.8 GB | Fits | Get file → | |
| IQ2_XS | 1.0 GB | 1.8 GB | Fits | Get file → | |
| IQ2_S | 1.1 GB | 1.9 GB | Fits | Get file → | |
| IQ2_M | 1.1 GB | 1.9 GB | Fits | Get file → | |
| Q2_K_S | 1.2 GB | 2.0 GB | Fits | Get file → | |
| Q2_K | 1.3 GB | 2.1 GB | Fits | Get file → | |
| IQ3_XXS | 1.3 GB | 2.1 GB | Fits | Get file → | |
| IQ3_XS | 1.4 GB | 2.2 GB | Fits | Get file → | |
| Q3_K_S | 1.5 GB | 2.3 GB | Fits | Get file → | |
| IQ3_S | 1.5 GB | 2.3 GB | Fits | Get file → | |
| IQ3_M | 1.5 GB | 2.3 GB | Fits | Get file → | |
| Q3_K_M | 1.6 GB | 2.4 GB | Fits | Get file → | |
| Q3_K_L | 1.7 GB | 2.5 GB | Fits | Get file → | |
| IQ4_XS | 1.7 GB | 2.5 GB | Fits | Get file → | |
| IQ4_NL | 1.8 GB | 2.6 GB | Fits | Get file → | |
| Q4_0 | 1.8 GB | 2.6 GB | Fits | Get file → | |
| Q4_K_S | 1.8 GB | 2.6 GB | Fits | Get file → | |
| Q4_K_M | 1.9 GB | 2.7 GB | Fits | Get file → | |
| Q4_1 | 2.0 GB | 2.8 GB | Fits | Get file → | |
| Q5_K_S | 2.2 GB | 3.0 GB | Fits | Get file → | |
| Q5_K_M | 2.2 GB | 3.0 GB | Fits | Get file → | |
| Q6_K | 2.5 GB | 3.3 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 1.93 GB, estimated 2.7 GB memory). If 4 GB VRAM is available, choose Q4_0 (1.83 GB, 2.6 GB memory). For CPU‑only or very low memory, IQ1_S (0.79 GB, 1.6 GB memory) is a lightweight option.
What GPU do you need for Jina Embeddings v4 Vllm Retrieval?
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).
Which Jina Embeddings v4 Vllm Retrieval quant should you choose?
Q4_K_M is the usual starting point for Jina Embeddings v4 Vllm Retrieval: it balances file size and quality well. Here it is a 1.9 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Jina Embeddings v4 Vllm Retrieval
How much VRAM does Jina Embeddings v4 Vllm Retrieval 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 Vllm Retrieval on an 8 GB GPU?
Yes, with Q6_K: the 2.5 GB file needs about 3.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Jina Embeddings v4 Vllm Retrieval GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 0.8 GB, IQ1_M is 0.9 GB, IQ2_XXS is 0.9 GB, IQ2_XS is 1.0 GB, IQ2_S is 1.1 GB and 19 more.
What context length does Jina Embeddings v4 Vllm Retrieval 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 Vllm Retrieval GGUF?
The files are on Hugging Face in the mradermacher/jina-embeddings-v4-vllm-retrieval-i1-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 Jina Embeddings v4 Vllm Retrieval use?
Hugging Face lists the license as cc-by-nc-4.0. 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, the Q4_K_M quant uses about 2.7 GB memory at 8k context, fitting within 8 GB VRAM.
Does this model support vision inputs?
The GGUF release is a vision model, but no mmproj files are included; it focuses on embedding generation.
What license applies to this model?
The model is licensed under cc‑by‑nc‑4.0, allowing non‑commercial use with attribution.