• jinaai/jina-code-embeddings-1.5b

The GGUF version of the code embedding model trained by Jina AI.

Jina Code Embeddings: A Small but Performant Code Embedding Model

Intended Usage & Model Info

jina-code-embeddings-1.5b-GGUF is the GGUF export of our jina-code-embeddings-1.5b, built on Qwen/Qwen2.5-Coder-1.5B.

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

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:

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"
  }
}

Install llama.cpp

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

./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

./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 to offload layers to GPU. Max context is 32768 but stick to --ubatch-size ≤ 8192 for best results.

Native endpoint (/embedding)

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`)

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