Store › model › Embeddings
nomic-embed-code-GGUF
by nomic-ai · source Hugging Face · updated 2025-05-01
apache-2.04.1 GB~6 GB RAMsource aliveunlabeled
Llama.cpp Quantizations of Nomic Embed Code: A State-of-the-Art Code Retriever
Add to LogiShell Open in the web IDE
The button opens LogiShell with this card; nothing installs from a link by itself. Inside the app the install goes through lsh models install hf:nomic-ai/nomic-embed-code-GGUF and its progress lives in the Resource Center.
Source and license
- Source: https://huggingface.co/nomic-ai/nomic-embed-code-GGUF
- License: apache-2.0
- Requirements: about 6 GB of RAM, 4.1 GB on disk (estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models). Runs with llama.cpp.
- Tags:
ggufsentence-similarityfeature-extractionendpoints_compatible
Numbers
- 2,438 downloads on Hugging Face
- 16 likes
- license apache-2.0
- 4.1 GB for nomic-embed-code.Q4_K_M.gguf
- 4,402,710 npm downloads a week for @huggingface/transformers
- latest @huggingface/transformers@4.3.0
Numbers as of 2026-10-02 21:01 UTC, from the source API.
Summary
Summary not ready yet: the numbers are here, the text is not. It is written by the collector through the LogiShell model facade when a provider key is present.
Reviews
No reviews yet. Reviews are written inside LogiShell: open this card in the app.
Files
| file | quant | size |
|---|---|---|
nomic-embed-code.Q2_K.gguf | Q2_K | 2.6 GB |
nomic-embed-code.Q3_K_L.gguf | Q3_K_L | 3.6 GB |
nomic-embed-code.Q3_K_M.gguf | Q3_K_M | 3.3 GB |
nomic-embed-code.Q3_K_S.gguf | Q3_K_S | 3.0 GB |
nomic-embed-code.Q4_0.gguf | Q4_0 | 3.8 GB |
nomic-embed-code.Q4_1.gguf | Q4_1 | 4.2 GB |
nomic-embed-code.Q4_K_M.gguf | Q4_K_M | 4.1 GB |
nomic-embed-code.Q4_K_S.gguf | Q4_K_S | 3.9 GB |
nomic-embed-code.Q5_K_M.gguf | Q5_K_M | 4.7 GB |
nomic-embed-code.Q5_K_S.gguf | Q5_K_S | 4.6 GB |
nomic-embed-code.Q6_K.gguf | Q6_K | 5.4 GB |
nomic-embed-code.Q8_0.gguf | Q8_0 | 7.0 GB |
nomic-embed-code.bf16.gguf | BF16 | 13 GB |
nomic-embed-code.f16.gguf | F16 | 13 GB |
nomic-embed-code.f32.gguf | F32 | 26 GB |
From the source README
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:
```python
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)
Card id model:hf:nomic-ai/nomic-embed-code-GGUF · collected 2026-10-02 21:01 UTC · JSON