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.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
JI
Jina Embeddings v5 Text Nano Retrieval
Jina · jinaai
Params212M
Context8K
Q4_K_M0.2 GB
CodingEmbedding
JI
Jina Embeddings v5 Text Small Retrieval
Jina · jinaai
Params596M
Context40K
Q4_K_M0.4 GB
Embedding
JI
jina reranker v1 tiny en
Jina · mradermacher
Params33M
Context8K
Q4_K_M0.0 GB
CodingEmbedding
JI
Jina Embeddings v5 Text Small Classification
Jina · jinaai
Params596M
Context32K
Q4_K_M0.4 GB
Embedding
JI
jina embeddings v4 text retrieval
Jina · jinaai
Params3.1B
Context125K
Q4_K_M1.9 GB
EmbeddingVision
JI
Jina Embeddings v5 Text Small Text Matching
Jina · jinaai
Params596M
Context32K
Q4_K_M0.4 GB
Embedding
JI
Jina Embeddings v5 Text Nano Text Matching
Jina · jinaai
Params212M
Context8K
Q4_K_M0.2 GB
CodingEmbedding
JI
Jina Embeddings v5 Text Nano Classification
Jina · jinaai
Params212M
Context8K
Q4_K_M0.2 GB
CodingEmbedding
JI
Jina Embeddings v5 Text Small Clustering
Jina · jinaai
Params596M
Context32K
Q4_K_M0.4 GB
Embedding
JI
jina embeddings v4 text matching
Jina · jinaai
Params3.1B
Context125K
Q4_K_M1.9 GB
Embedding
JI
Jina Reranker v3.5
Jina · jinaai
Params596M
Context128K
Q4_K_M0.4 GB
Embedding
JI
jina embeddings v2 base code
Jina · second-state
Params160M
Context8K
Q4_K_M0.1 GB
CodingEmbedding
JI
jina embeddings v4 text code
Jina · jinaai
Params3.1B
Context125K
Q4_K_M1.9 GB
CodingEmbedding
JI
jina reranker v1 tiny en
Jina · gpustack
Params33M
Context8K
Q4_K_M0.0 GB
CodingEmbedding
JI
jina ocr v1
Jina · ahmadw
Params2.93B
Context—
Q4_K_M2.0 GB
GGUF
JI
Jina Embeddings v5 Text Nano Clustering
Jina · jinaai
Params212M
Context8K
Q4_K_M0.2 GB
CodingEmbedding
JI
jina embeddings v5 omni nano classification
Jina · jinaai
Params212M
Context8K
Q4_K_M0.2 GB
EmbeddingVision
JI
Jina Reranker M0
Jina · jinaai
Params1.54B
Context32K
Q4_K_M1.0 GB
Embedding
JI
jina embeddings v2 base code Q8 0
Jina · ggml-org
Params160M
Context8K
Smallest0.2 GB
CodingEmbedding
JI
jina embeddings v5 omni small retrieval
Jina · jinaai
Params596M
Context32K
Q4_K_M0.4 GB
EmbeddingVision
JI
Jina Reranker v2 Base Multilingual
Jina · gpustack
Params278M
Context1K
Q4_K_M0.2 GB
CodingEmbedding
JI
jina embeddings v2 base es
Jina · second-state
Params160M
Context8K
Q4_K_M0.1 GB
CodingEmbedding
JI
jina embeddings v5 omni nano retrieval
Jina · jinaai
Params212M
Context8K
Q4_K_M0.2 GB
EmbeddingVision
JI
jina embeddings v5 omni nano clustering
Jina · jinaai
Params212M
Context8K
Q4_K_M0.2 GB
EmbeddingReasoningTool use
JI
Jina Embeddings v4 Vllm Retrieval
Jina · mradermacher
Params3.1B
Context125K
Q4_K_M1.9 GB
Embedding
JI
jina embeddings v2 base de
Jina · second-state
Params160M
Context8K
Q4_K_M0.1 GB
CodingEmbedding
JI
jina embeddings v5 omni small text matching
Jina · jinaai
Params596M
Context32K
Q4_K_M0.4 GB
EmbeddingReasoningTool use
JI
jina embeddings v2 base en
Jina · second-state
Params137M
Context8K
Q4_K_M0.1 GB
CodingEmbedding
JI
jina-reranker-v3
Jina · jinaai
Params596M
Context128K
Q4_K_M0.4 GB
Embedding
JI
jina embeddings v5 omni small classification
Jina · jinaai
Params596M
Context32K
Q4_K_M0.4 GB
EmbeddingReasoningTool use

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.

Keep browsing