Jina GGUF models
109 GGUF models in the Jina family, quantized by 37 uploaders. Sizes run from 32M to 3.34B parameters. The longest trained context is 128K tokens.
About the Jina GGUF models
Jina is represented on ggufmodels.com by 109 GGUF models, quantized by 37 uploaders on Hugging Face. The most downloaded are Jina Embeddings v5 Text Nano Retrieval, Jina Embeddings v5 Text Small Retrieval and jina reranker v1 tiny en. Parameter counts run from 32M to 3.34B, and the longest trained context window is 128K tokens.
A Q4_K_M file of a Jina model is between 0.0 to 2.0 GB, which is the quant most people start with. Most files come from jinaai (22), sinjab (9) and mradermacher (9). The quants you will meet most often are Q8_0 (75), Q4_K_M (68), Q5_K_M (56) and Q2_K (51), where the number is how many models offer that quant.
Frequently asked questions
Which Jina GGUF should I download?
The most downloaded Jina GGUF here is Jina Embeddings v5 Text Nano Retrieval. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.
How much VRAM does a Jina model need?
Q4_K_M files of Jina models on this site range from 0.0 to 2.0 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.
Where do Jina GGUF files come from?
The most common quantizers here are jinaai, sinjab and mradermacher. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.