Instructions to use bigsk1/jarvis-embedding-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bigsk1/jarvis-embedding-GGUF with sentence-transformers:

from sentence_transformers import SentenceTransformer

model = SentenceTransformer("bigsk1/jarvis-embedding-GGUF")

sentences = [
    "That is a happy person",
    "That is a happy dog",
    "That is a very happy person",
    "Today is a sunny day"
]
embeddings = model.encode(sentences)

similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [4, 4]

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use bigsk1/jarvis-embedding-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf bigsk1/jarvis-embedding-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf bigsk1/jarvis-embedding-GGUF:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf bigsk1/jarvis-embedding-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf bigsk1/jarvis-embedding-GGUF:BF16

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf bigsk1/jarvis-embedding-GGUF:BF16
# Run inference directly in the terminal:
./llama-cli -hf bigsk1/jarvis-embedding-GGUF:BF16

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf bigsk1/jarvis-embedding-GGUF:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf bigsk1/jarvis-embedding-GGUF:BF16

Use Docker

docker model run hf.co/bigsk1/jarvis-embedding-GGUF:BF16

LM Studio
Jan
Ollama
How to use bigsk1/jarvis-embedding-GGUF with Ollama:
```
ollama run hf.co/bigsk1/jarvis-embedding-GGUF:BF16
```

Unsloth Studio

How to use bigsk1/jarvis-embedding-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for bigsk1/jarvis-embedding-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for bigsk1/jarvis-embedding-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for bigsk1/jarvis-embedding-GGUF to start chatting

Docker Model Runner
How to use bigsk1/jarvis-embedding-GGUF with Docker Model Runner:
```
docker model run hf.co/bigsk1/jarvis-embedding-GGUF:BF16
```

Lemonade

How to use bigsk1/jarvis-embedding-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull bigsk1/jarvis-embedding-GGUF:BF16

Run and chat with the model

lemonade run user.jarvis-embedding-GGUF-BF16

List all available models

lemonade list

Atomic Chat

Access Jarvis Embedding

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

This artifact is distributed under the Gemma Terms of Use. By requesting access, you acknowledge those terms and the Gemma Prohibited Use Policy.

Jarvis Embedding — EmbeddingGemma 300M BF16 GGUF

This repository is the disaster-recovery mirror for the immutable embedding artifact used by Jarvis Voice in both cloud and local modes.

The normal installation path is Ollama:

ollama pull bigsk1/jarvis-embedding:bf16-v1

Jarvis always calls an Ollama /api/embed endpoint. This Hugging Face repository is an artifact backup, not a separate runtime embedding provider.

Artifact identity

Field	Pinned value
GGUF file	`jarvis-embedding-bf16-v1.gguf`
GGUF SHA-256	`0800cbac9c2064dde519420e75e512a83cb360de3ad5df176185dc69652fc515`
GGUF size	`621867104` bytes
Ollama tag	`bigsk1/jarvis-embedding:bf16-v1`
Ollama manifest SHA-256	`85462619ee721b466c5927d109d4cb765861907d5417b9109caebc4e614679f1`
Ollama source artifact	`embeddinggemma:300m-bf16`
Base model	`google/embeddinggemma-300m`
Architecture	Gemma 3 embedding model
Parameters	307.58M
Tensor precision	BF16
Output dimensions	768
Context window	2048 tokens
Pooling	Mean

The GGUF is byte-for-byte identical to the model layer in the pinned Ollama manifest. Representative query, document, and similarity inputs produced bit-for-bit identical normalized vectors between the upstream Ollama artifact and the versioned Jarvis tag before publication.

Modification notice

Google's upstream EmbeddingGemma model was converted to GGUF BF16 by Ollama. The Jarvis project did not train, fine-tune, or alter the model tensors from Ollama's embeddinggemma:300m-bf16 artifact. Jarvis assigned a versioned Ollama alias and published this recovery mirror and its provenance metadata.

Prompt contract

Jarvis applies Google's asymmetric EmbeddingGemma prompt formats before calling Ollama:

Query:      task: search result | query: {text}
Document:   title: {title-or-none} | text: {text}
Similarity: task: sentence similarity | query: {text}

Persisted Jarvis embeddings also fingerprint the model tag, Ollama manifest digest, dimensions, prompt profile, and prompt role. A mismatch fails closed so vectors from incompatible artifacts cannot be mixed.

Verify the download

sha256sum -c SHA256SUMS

The expected model-layer digest is 0800cbac9c2064dde519420e75e512a83cb360de3ad5df176185dc69652fc515.

Rebuild into Ollama when the registry is unavailable

Download the repository after acknowledging the Gemma terms, then create a new local recovery tag from the included Modelfile:

hf download bigsk1/jarvis-embedding-GGUF --local-dir jarvis-embedding-GGUF
cd jarvis-embedding-GGUF
sha256sum -c SHA256SUMS
ollama create jarvis-embedding-recovered:bf16-v1 -f Modelfile

Important: this is a weight-level rebuild, not a drop-in restoration of the pinned Ollama manifest. In a live recovery test, Ollama 0.32.13 reserialized the GGUF and added a template layer. Query, document, and similarity vectors remained bit-for-bit identical at 768 dimensions, but the rebuilt manifest digest differed from the pinned digest.

To adopt a rebuilt artifact, publish it under a new immutable tag, update the configured model fingerprint, and rebuild every persisted Jarvis embedding namespace. Never make the existing bf16-v1 identity accept a different digest. The exact original manifest and all of its source layer bytes are archived here for a registry-level restoration workflow; do not modify Ollama's private model store directly.

Provenance files

ollama/manifest-bf16-v1.json is the exact registry manifest body.
ollama/config.json and ollama/params.json preserve the exact small Ollama layers referenced by that manifest.
LICENSE preserves the Gemma Terms bundled in the Ollama artifact.
Modelfile is a convenience rebuild recipe; it does not promise the same Ollama manifest digest after import.
NOTICE contains Google's required redistribution notice.
ARTIFACT.json provides machine-readable identity metadata.

License

This artifact is provided under and subject to the Gemma Terms of Use and the incorporated Gemma Prohibited Use Policy. See LICENSE and NOTICE in this repository.

Downloads last month: 1

GGUF

Model size

0.3B params

Architecture

gemma3

Hardware compatibility

16-bit

Model tree for bigsk1/jarvis-embedding-GGUF

Base model

google/embeddinggemma-300m

Quantized

(301)

this model