nomic-ai/nomic-embed-code-GGUF

Llama.cpp Quantizations of Nomic Embed Code: A State-of-the-Art Code Retriever

Blog | Technical Report | AWS SageMaker | Atlas Embedding and Unstructured Data Analytics Platform

Using llama.cpp commit 11683f579 for quantization.

Original model: nomic-embed-code

Usage

This model can be used with the llama.cpp server and other software that supports llama.cpp embedding models.

Queries embedded with nomic-embed-code must begin with the following prefix:

Represent this query for searching relevant code:

For example, the code below shows how to use the prefix to embed user questions, e.g. in a RAG application.

Start a llama.cpp server:

llama-server -m nomic-embed-code.Q4_0.gguf --embeddings --pooling last

And run this code:

import requests
from textwrap import dedent

def dot(va, vb):
    return sum(a*b for a, b in zip(va, vb))
def embed(texts):
    resp = requests.post('http://localhost:8080/v1/embeddings', json={'input': texts}).json()
    return [d['embedding'] for d in resp['data']]

docs = [
    dedent("""\
    def fn(n):
        if n < 0:
            raise ValueError
        return 1 if n == 0 else n * fn(n - 1)
    """).strip(),
    dedent("""\
    def fn(n):
        print(("Fizz" * (n % 3 == 0) + "Buzz" * (n % 5 == 0)) or n)
    """).strip(),
]
docs_embed = embed(docs)

query = 'Calculate the n-th factorial'
query_embed = embed(['Represent this query for searching relevant code: ' + query])[0]
print(f'query: {query!r}')
for d, e in zip(docs, docs_embed):
    print(f'\nsimilarity {dot(query_embed, e):.2f}:\n{d}')

You should see output similar to this:

query: 'Calculate the n-th factorial'

similarity 0.49:
def fn(n):
    if n < 0:
        raise ValueError
    return 1 if n == 0 else n * fn(n - 1)

similarity 0.32:
def fn(n):
    print(("Fizz" * (n % 3 == 0) + "Buzz" * (n % 5 == 0)) or n)

Download a file (not the whole branch) from below:

Filename	Quant Type	File Size	Description
nomic-embed-code.f32.gguf	f32	26.35GiB	Full FP32 weights.
nomic-embed-code.f16.gguf	f16	13.18GiB	Full FP16 weights.
nomic-embed-code.bf16.gguf	bf16	13.18GiB	Full BF16 weights.
nomic-embed-code.Q8_0.gguf	Q8_0	7.00GiB	Extremely high quality, generally unneeded but max available quant.
nomic-embed-code.Q6_K.gguf	Q6_K	5.41GiB	Very high quality, near perfect, recommended.
nomic-embed-code.Q5_K_M.gguf	Q5_K_M	4.72GiB	High quality, recommended.
nomic-embed-code.Q5_K_S.gguf	Q5_K_S	4.60GiB	High quality, recommended.
nomic-embed-code.Q4_1.gguf	Q4_1	4.22GiB	Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon.
nomic-embed-code.Q4_K_M.gguf	Q4_K_M	4.08GiB	Good quality, default size for most use cases, recommended.
nomic-embed-code.Q4_K_S.gguf	Q4_K_S	3.87GiB	Slightly lower quality with more space savings, recommended.
nomic-embed-code.Q4_0.gguf	Q4_0	3.84GiB	Legacy format, offers online repacking for ARM and AVX CPU inference.
nomic-embed-code.Q3_K_L.gguf	Q3_K_L	3.59GiB	Lower quality but usable, good for low RAM availability.
nomic-embed-code.Q3_K_M.gguf	Q3_K_M	3.33GiB	Low quality.
nomic-embed-code.Q3_K_S.gguf	Q3_K_S	3.03GiB	Low quality, not recommended.
nomic-embed-code.Q2_K.gguf	Q2_K	2.64GiB	Very low quality but surprisingly usable.

Model Overview

nomic-embed-code is a state-of-the-art code embedding model that excels at code retrieval tasks:

• High Performance: Outperforms Voyage Code 3 and OpenAI Embed 3 Large on CodeSearchNet
• Multilingual Code Support: Trained for multiple programming languages (Python, Java, Ruby, PHP, JavaScript, Go)
• Advanced Architecture: 7B parameter code embedding model
• Fully Open-Source: Model weights, training data, and evaluation code released

Model	Python	Java	Ruby	PHP	JavaScript	Go
Nomic Embed Code	81.7	80.5	81.8	72.3	77.1	93.8
Voyage Code 3	80.8	80.5	84.6	71.7	79.2	93.2
OpenAI Embed 3 Large	70.8	72.9	75.3	59.6	68.1	87.6
Nomic CodeRankEmbed-137M	78.4	76.9	79.3	68.8	71.4	92.7
CodeSage Large v2 (1B)	74.2	72.3	76.7	65.2	72.5	84.6
CodeSage Large (1B)	70.8	70.2	71.9	61.3	69.5	83.7
Qodo Embed 1 7B	59.9	61.6	68.4	48.5	57.0	81.4

Model Architecture

• Total Parameters: 7B
• Training Approach: Trained on the CoRNStack dataset with dual-consistency filtering and progressive hard negative mining
• Supported Languages: Python, Java, Ruby, PHP, JavaScript, and Go

CoRNStack Dataset Curation

Starting with the deduplicated Stackv2, we create text-code pairs from function docstrings and respective code. We filtered out low-quality pairs where the docstring wasn't English, too short, or that contained URLs, HTML tags, or invalid characters. We additionally kept docstrings with text lengths of 256 tokens or longer to help the model learn long-range dependencies.

After the initial filtering, we used dual-consistency filtering to remove potentially noisy examples. We embed each docstring and code pair and compute the similarity between each docstring and every code example. We remove pairs from the dataset if the corresponding code example is not found in the top-2 most similar examples for a given docstring.

During training, we employ a novel curriculum-based hard negative mining strategy to ensure the model learns from challenging examples. We use a softmax-based sampling strategy to progressively sample hard negatives with increasing difficulty over time.

Join the Nomic Community

• Nomic Embed Ecosystem: https://www.nomic.ai/embed
• Website: https://nomic.ai
• Twitter: https://twitter.com/nomic_ai
• Discord: https://discord.gg/myY5YDR8z8

Citation

If you find the model, dataset, or training code useful, please cite our work:

@misc{suresh2025cornstackhighqualitycontrastivedata,
      title={CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking},
      author={Tarun Suresh and Revanth Gangi Reddy and Yifei Xu and Zach Nussbaum and Andriy Mulyar and Brandon Duderstadt and Heng Ji},
      year={2025},
      eprint={2412.01007},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2412.01007},
}