Store › model › Embeddings
jina-embeddings-v5-text-nano-clustering
by jinaai · source Hugging Face · updated 2026-04-15
cc-by-nc-4.0150 MB~1 GB RAMsource aliveunlabeled
jina-embeddings-v5-text: Task-Targeted Embedding Distillation
Add to LogiShell Open in the web IDE
The button opens LogiShell with this card; nothing installs from a link by itself. Inside the app the install goes through lsh models install hf:jinaai/jina-embeddings-v5-text-nano-clustering and its progress lives in the Resource Center.
Source and license
- Source: https://huggingface.co/jinaai/jina-embeddings-v5-text-nano-clustering
- License: cc-by-nc-4.0 (restricted license: terms at the source apply)
- Requirements: about 1 GB of RAM, 150 MB on disk (estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models). Runs with llama.cpp.
- Tags:
llama.cpponnxsafetensorsggufeurobertembeddingllama-cppjina-embeddings-v5feature-extractionmtebvllmsentence-transformerscustom_codemultilingual
Numbers
- 2,677 downloads on Hugging Face
- 5 likes
- license cc-by-nc-4.0
- 0.1 GB for v5-nano-clustering-Q4_K_M.gguf
- 327,838 npm downloads a week for node-llama-cpp
- latest node-llama-cpp@3.22.1
Numbers as of 2026-10-02 20:59 UTC, from the source API.
Summary
Summary not ready yet: the numbers are here, the text is not. It is written by the collector through the LogiShell model facade when a provider key is present.
Reviews
No reviews yet. Reviews are written inside LogiShell: open this card in the app.
Files
| file | quant | size |
|---|---|---|
model.safetensors | 404 MB | |
onnx/model.onnx | 89 KB | |
onnx/model_fp16.onnx | 90 KB | |
onnx/model_q4.onnx | 126 KB | |
onnx/model_q4f16.onnx | F16 | 127 KB |
onnx/model_quantized.onnx | 128 KB | |
v5-nano-clustering-F16.gguf | F16 | 411 MB |
v5-nano-clustering-IQ1_M.gguf | IQ1_M | 97 MB |
v5-nano-clustering-IQ1_S.gguf | IQ1_S | 95 MB |
v5-nano-clustering-IQ2_M.gguf | IQ2_M | 108 MB |
v5-nano-clustering-IQ2_XXS.gguf | IQ2_XXS | 101 MB |
v5-nano-clustering-IQ4_NL.gguf | IQ4_NL | 145 MB |
v5-nano-clustering-IQ4_XS.gguf | IQ4_XS | 142 MB |
v5-nano-clustering-Q2_K.gguf | Q2_K | 124 MB |
v5-nano-clustering-Q3_K_M.gguf | Q3_K_M | 137 MB |
v5-nano-clustering-Q4_K_M.gguf | Q4_K_M | 150 MB |
v5-nano-clustering-Q5_K_M.gguf | Q5_K_M | 161 MB |
v5-nano-clustering-Q5_K_S.gguf | Q5_K_S | 159 MB |
v5-nano-clustering-Q6_K.gguf | Q6_K | 173 MB |
v5-nano-clustering-Q8_0.gguf | Q8_0 | 222 MB |
From the source README
jina-embeddings-v5-text: Task-Targeted Embedding Distillation
Elastic Inference Service | ArXiv | Release Note | Blog
Model Overview
`jina-embeddings-v5-text-nano-clustering` is a compact, high-performance text embedding model designed for clustering.
It is part of the jina-embeddings-v5-text model family, which also includes jina-embeddings-v5-text-small, for better performance at a bigger size.
Trained using a novel approach that combines distillation with task-specific contrastive losses, `jina-embeddings-v5-text-nano-clustering` outperforms existing state-of-the-art models of similar size across diverse embedding benchmarks.
| Feature | Value |
| --- | --- |
| Parameters | 239M |
| Supported Tasks | `clustering` |
| Max Sequence Length | 8192 |
| Embedding Dimension | 768 |
| Matryoshka Dimensions | 32, 64, 128, 256, 512, 768 |
| Pooling Strategy | Last-token pooling |
| Base Model | jinaai/jina-embeddings-v5-text-nano |
Training and Evaluation
For training details and evaluation results, see our technical report.
Usage
Requirements
The following Python packages are required:
- `transformers>=5.1.0`
- `torch>=2.8.0`
- `peft>=0.15.2`
- `vllm==0.15.1`
Card id model:hf:jinaai/jina-embeddings-v5-text-nano-clustering · collected 2026-10-02 20:59 UTC · JSON