Instructions to use usefulname/vocafant-scan-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use usefulname/vocafant-scan-model 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 usefulname/vocafant-scan-model:Q8_0
# Run inference directly in the terminal:
llama cli -hf usefulname/vocafant-scan-model:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf usefulname/vocafant-scan-model:Q8_0
# Run inference directly in the terminal:
llama cli -hf usefulname/vocafant-scan-model:Q8_0

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 usefulname/vocafant-scan-model:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf usefulname/vocafant-scan-model:Q8_0

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 usefulname/vocafant-scan-model:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf usefulname/vocafant-scan-model:Q8_0

Use Docker

docker model run hf.co/usefulname/vocafant-scan-model:Q8_0

LM Studio
Jan
Ollama
How to use usefulname/vocafant-scan-model with Ollama:
```
ollama run hf.co/usefulname/vocafant-scan-model:Q8_0
```

Unsloth Studio

How to use usefulname/vocafant-scan-model 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 usefulname/vocafant-scan-model 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 usefulname/vocafant-scan-model to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for usefulname/vocafant-scan-model to start chatting

Docker Model Runner
How to use usefulname/vocafant-scan-model with Docker Model Runner:
```
docker model run hf.co/usefulname/vocafant-scan-model:Q8_0
```

Lemonade

How to use usefulname/vocafant-scan-model with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull usefulname/vocafant-scan-model:Q8_0

Run and chat with the model

lemonade run user.vocafant-scan-model-Q8_0

List all available models

lemonade list

Atomic Chat

VocaFant Scan Model

Unmodified GGUF quantizations of Qwen/Qwen3-VL-2B-Instruct (Apache-2.0, © Alibaba Cloud / Qwen Team), re-hosted for the VocaFant app's on-device vocabulary-page recognition. Files originate from the official Qwen/Qwen3-VL-2B-Instruct-GGUF repo.

File	Purpose
`Qwen3VL-2B-Instruct-Q4_K_M.gguf`	model weights, 4-bit K-quant
`mmproj-Qwen3VL-2B-Instruct-Q8_0.gguf`	multimodal projector (vision input)

The app downloads these temporarily (recognize → enrich → delete), verifies SHA-256 against a revision-pinned manifest, and never uploads user photos anywhere. No fine-tuning was performed; the weights are byte-identical to the official release.

License: Apache-2.0 (inherited from the base model — see LICENSE in the base repo).

Downloads last month: 50

GGUF

Model size

0.6B params

Architecture

qwen3

Hardware compatibility

4-bit

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for usefulname/vocafant-scan-model

Base model

Qwen/Qwen3-VL-2B-Instruct

Quantized

(88)

this model