Instructions to use batiai/Qwen3-VL-Embedding-2B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use batiai/Qwen3-VL-Embedding-2B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="batiai/Qwen3-VL-Embedding-2B-GGUF",
	filename="Qwen3-VL-Embedding-2B-Q6_K.gguf",
)

llm.create_chat_completion(
	messages = "{\n    \"source_sentence\": \"That is a happy person\",\n    \"sentences\": [\n        \"That is a happy dog\",\n        \"That is a very happy person\",\n        \"Today is a sunny day\"\n    ]\n}"
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use batiai/Qwen3-VL-Embedding-2B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf batiai/Qwen3-VL-Embedding-2B-GGUF:Q6_K
# Run inference directly in the terminal:
llama-cli -hf batiai/Qwen3-VL-Embedding-2B-GGUF:Q6_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf batiai/Qwen3-VL-Embedding-2B-GGUF:Q6_K
# Run inference directly in the terminal:
llama-cli -hf batiai/Qwen3-VL-Embedding-2B-GGUF:Q6_K

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 batiai/Qwen3-VL-Embedding-2B-GGUF:Q6_K
# Run inference directly in the terminal:
./llama-cli -hf batiai/Qwen3-VL-Embedding-2B-GGUF:Q6_K

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 batiai/Qwen3-VL-Embedding-2B-GGUF:Q6_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf batiai/Qwen3-VL-Embedding-2B-GGUF:Q6_K

Use Docker

docker model run hf.co/batiai/Qwen3-VL-Embedding-2B-GGUF:Q6_K

LM Studio
Jan
Ollama
How to use batiai/Qwen3-VL-Embedding-2B-GGUF with Ollama:
```
ollama run hf.co/batiai/Qwen3-VL-Embedding-2B-GGUF:Q6_K
```

Unsloth Studio

How to use batiai/Qwen3-VL-Embedding-2B-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 batiai/Qwen3-VL-Embedding-2B-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 batiai/Qwen3-VL-Embedding-2B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for batiai/Qwen3-VL-Embedding-2B-GGUF to start chatting

How to use batiai/Qwen3-VL-Embedding-2B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf batiai/Qwen3-VL-Embedding-2B-GGUF:Q6_K

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "batiai/Qwen3-VL-Embedding-2B-GGUF:Q6_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use batiai/Qwen3-VL-Embedding-2B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf batiai/Qwen3-VL-Embedding-2B-GGUF:Q6_K

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default batiai/Qwen3-VL-Embedding-2B-GGUF:Q6_K

Run Hermes

hermes

Docker Model Runner
How to use batiai/Qwen3-VL-Embedding-2B-GGUF with Docker Model Runner:
```
docker model run hf.co/batiai/Qwen3-VL-Embedding-2B-GGUF:Q6_K
```

Lemonade

How to use batiai/Qwen3-VL-Embedding-2B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull batiai/Qwen3-VL-Embedding-2B-GGUF:Q6_K

Run and chat with the model

lemonade run user.Qwen3-VL-Embedding-2B-GGUF-Q6_K

List all available models

lemonade list

Qwen3-VL-Embedding-2B GGUF — Quantized by BatiAI

GGUF quantizations of Qwen/Qwen3-VL-Embedding-2B — the most-downloaded vision-language embedding model of 2026 (1.64 M downloads on HF). Part of BatiAI's on-device RAG stack for BatiFlow.

What does it do?

VL (Vision-Language) embedding turns either text OR images into dense vectors. Same embedding space means:

Search photos by text — "beach sunset" retrieves matching photos without manual tagging
Search text by image — drop a screenshot, find similar notes
Cross-modal RAG — index PDFs, notes, and images together in one vector DB

Quick Start

Text embedding (llama.cpp, via Ollama)

ollama pull batiai/qwen3-vl-embed-2b:q8

curl http://localhost:11434/api/embeddings -d '{
  "model": "batiai/qwen3-vl-embed-2b:q8",
  "prompt": "What is the capital of France?"
}'

Image embedding

Image embedding requires llama.cpp's mtmd (multimodal) build. See Qwen3-VL docs for batch image encoding.

Available Quantizations

File	Quant	Size	Recommended
`Qwen3-VL-Embedding-2B-Q6_K.gguf`	Q6_K	~1.5 GB	balanced (recommended default)
`Qwen3-VL-Embedding-2B-Q8_0.gguf`	Q8_0	~1.8 GB	near-lossless embeddings

Embedding models are sensitive to low-bit quantization (vector quality drops). Q6_K minimum.

Quality note

Direct embedding-quality eval (e.g. MTEB retrieval) is more involved than rerank pairwise testing and takes longer to run locally. Our sibling reranker card shows that Q6_K ↔ Q8_0 drift is negligible (Pearson r = 0.998 on 40 pairs) for the same model family — we expect the embedding model to behave similarly. MTEB/BEIR numbers will be added as measured.

Why Qwen3-VL-Embedding?

SOTA on MTEB — top multilingual embedding model across text + image
Multilingual — en / ko / ja / zh
Multimodal — text and image in the same embedding space
2048-dim vectors — balance between expressiveness and storage

Why BatiAI?

Quantized directly from Alibaba's BF16 safetensors
BatiAI-signed metadata
Part of a full on-device RAG stack

Technical Details

Original Model: Qwen/Qwen3-VL-Embedding-2B
Architecture: Qwen3-VL with pooling head
Parameters: 2 B (text tower) + vision tower
Embedding dim: 2048
Max context: 32 K (text)
License: Apache 2.0
Quantized with: llama.cpp

BatiAI's RAG Stack

Role	Model	HF
VL Embedding (2 B)	Qwen3-VL-Embedding-2B	this repo
Reranker (0.6 B)	Qwen3-Reranker-0.6B	batiai/Qwen3-Reranker-0.6B-GGUF
Reranker (4 B)	Qwen3-Reranker-4B	batiai/Qwen3-Reranker-4B-GGUF
Chat LLM (35 B-A3B)	Qwen3.6-35B-A3B	batiai/Qwen3.6-35B-A3B-GGUF