The model supports code retrieval and technical QA across 15+ programming languages and multiple domains, including web development, software development, machine learning, data science, and educational coding problems.

Key Features

Feature	Jina Code Embeddings 1.5B GGUF
Base Model	Qwen2.5-Coder-1.5B
Supported Tasks	`nl2code`, `code2code`, `code2nl`, `code2completion`, `qa`
Max Sequence Length	32768 (recommended ≤ 8192)
Embedding Vector Dim	1536
Matryoshka Dimensions	128, 256, 512, 1024, 1536 (client-side slice)
Pooling Strategy	MUST use `--pooling last` (EOS)

Matryoshka note: llama.cpp always returns 896-d embeddings for this model. To use 128, 256, 512, 1024, 1536, slice client-side (e.g., take the first k elements).

Task Instructions

Prefix inputs with task-specific instructions:

python

INSTRUCTION_CONFIG = {
  "nl2code": {
    "query": "Find the most relevant code snippet given the following query:\n",
    "passage": "Candidate code snippet:\n"
  },
  "qa": {
    "query": "Find the most relevant answer given the following question:\n",
    "passage": "Candidate answer:\n"
  },
  "code2code": {
    "query": "Find an equivalent code snippet given the following code snippet:\n",
    "passage": "Candidate code snippet:\n"
  },
  "code2nl": {
    "query": "Find the most relevant comment given the following code snippet:\n",
    "passage": "Candidate comment:\n"
  },
  "code2completion": {
    "query": "Find the most relevant completion given the following start of code snippet:\n",
    "passage": "Candidate completion:\n"
  }
}

Use the appropriate prefix for queries and passages at inference time.

Install `llama.cpp`

Follow the official instructions: https://github.com/ggml-org/llama.cpp

Model files

Hugging Face repo (GGUF): https://huggingface.co/jinaai/jina-code-embeddings-1.5b-GGUF

Pick a file (e.g., jina-code-embeddings-1.5b-F16.gguf). You can either:

auto-download by passing the repo and file directly to llama.cpp
use a local path with -m

HTTP service with `llama-server`

Auto-download from Hugging Face (repo + file)

bash

./llama-server \
  --embedding \
  --hf-repo jinaai/jina-code-embeddings-1.5b-GGUF \
  --hf-file jina-code-embeddings-1.5b-F16.gguf \
  --host 0.0.0.0 \
  --port 8080 \
  --ctx-size 32768 \
  --ubatch-size 8192 \
  --pooling last

Local file

bash

./llama-server \
  --embedding \
  -m /path/to/jina-code-embeddings-1.5b-F16.gguf \
  --host 0.0.0.0 \
  --port 8080 \
  --ctx-size 32768 \
  --ubatch-size 8192 \
  --pooling last

Tips: -ngl <N> to offload layers to GPU. Max context is 32768 but stick to --ubatch-size ≤ 8192 for best results.

Query examples (HTTP)

Native endpoint (`/embedding`)

bash

curl -X POST http://localhost:8080/embedding \
  -H "Content-Type: application/json" \
  -d '{
        "content": [
          "Find the most relevant code snippet given the following query:\nprint hello world in python",
          "Candidate code snippet:\nprint(\"Hello World!\")"
        ]
      }'

OpenAI-compatible (`/v1/embeddings`)

bash

curl http://localhost:8080/v1/embeddings \
  -H "Content-Type: application/json" \
  -d '{
        "input": [
          "Find the most relevant code snippet given the following query:\nprint hello world in python",
          "Candidate code snippet:\nprint(\"Hello World!\")"
        ]
      }'

Training & Evaluation

See our technical report: https://arxiv.org/abs/2508.21290

Contact

Join our Discord: https://discord.jina.ai

jinaai/jina-code-embeddings-1.5b-GGUF

Jina Code Embeddings: A Small but Performant Code Embedding Model

Intended Usage & Model Info

Key Features

Task Instructions

Install llama.cpp

Model files

HTTP service with llama-server

Auto-download from Hugging Face (repo + file)

Local file

Query examples (HTTP)

Native endpoint (/embedding)

OpenAI-compatible (/v1/embeddings)

Training & Evaluation

Contact

jinaai/
jina-code-embeddings-1.5b-GGUF

Install `llama.cpp`

HTTP service with `llama-server`

Native endpoint (`/embedding`)

OpenAI-compatible (`/v1/embeddings`)