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

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Kushtrim/Qwen3-VL-2B-Instruct-Shqip 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 Kushtrim/Qwen3-VL-2B-Instruct-Shqip:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Kushtrim/Qwen3-VL-2B-Instruct-Shqip:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Kushtrim/Qwen3-VL-2B-Instruct-Shqip:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Kushtrim/Qwen3-VL-2B-Instruct-Shqip:Q4_K_M

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 Kushtrim/Qwen3-VL-2B-Instruct-Shqip:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Kushtrim/Qwen3-VL-2B-Instruct-Shqip:Q4_K_M

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 Kushtrim/Qwen3-VL-2B-Instruct-Shqip:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Kushtrim/Qwen3-VL-2B-Instruct-Shqip:Q4_K_M

Use Docker

docker model run hf.co/Kushtrim/Qwen3-VL-2B-Instruct-Shqip:Q4_K_M

LM Studio
Jan

vLLM

How to use Kushtrim/Qwen3-VL-2B-Instruct-Shqip with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Kushtrim/Qwen3-VL-2B-Instruct-Shqip"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kushtrim/Qwen3-VL-2B-Instruct-Shqip",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/Kushtrim/Qwen3-VL-2B-Instruct-Shqip:Q4_K_M

Ollama
How to use Kushtrim/Qwen3-VL-2B-Instruct-Shqip with Ollama:
```
ollama run hf.co/Kushtrim/Qwen3-VL-2B-Instruct-Shqip:Q4_K_M
```
Unsloth Desktop

How to use Kushtrim/Qwen3-VL-2B-Instruct-Shqip with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Kushtrim/Qwen3-VL-2B-Instruct-Shqip:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Kushtrim/Qwen3-VL-2B-Instruct-Shqip:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Kushtrim/Qwen3-VL-2B-Instruct-Shqip with Docker Model Runner:
```
docker model run hf.co/Kushtrim/Qwen3-VL-2B-Instruct-Shqip:Q4_K_M
```

Lemonade

How to use Kushtrim/Qwen3-VL-2B-Instruct-Shqip with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Kushtrim/Qwen3-VL-2B-Instruct-Shqip:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3-VL-2B-Instruct-Shqip-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Kushtrim/Qwen3-VL-2B-Instruct-Shqip with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Kushtrim/Qwen3-VL-2B-Instruct-Shqip:Q4_K_M

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 Kushtrim/Qwen3-VL-2B-Instruct-Shqip:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Kushtrim/Qwen3-VL-2B-Instruct-Shqip with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Kushtrim/Qwen3-VL-2B-Instruct-Shqip:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "Kushtrim/Qwen3-VL-2B-Instruct-Shqip:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

You need to agree to share your contact information to access this model

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

Qwen3-VL-2B-Instruct-Shqip

Kushtrim/Qwen3-VL-2B-Instruct-Shqip is an Albanian-focused vision-language model based on unsloth/Qwen3-VL-2B-Instruct, finetuned primarily to improve OCR / transcription and document understanding for Albanian newspaper scans (e.g. Bujku).

What’s new vs the base model

Better Albanian OCR on scanned newspaper-style pages (noisy layouts, multi-column text, artifacts).
More consistent responses in Albanian (sq) for OCR and document-style prompts.

Model details

Type: vision-language (image + text → text)
Base model: unsloth/Qwen3-VL-2B-Instruct
Primary language: Albanian (sq)
License: Apache-2.0 (same as the base model)

Intended use

Use this model for:

OCR / transcription of Albanian text from images (scanned pages, photos of documents).
Document understanding: summarization, extraction, Q&A over an image of a page.
General multimodal chat in Albanian (image captioning, visual Q&A), with best results on document-like inputs.

How it was trained (high level)

Base: unsloth/Qwen3-VL-2B-Instruct (derived from Qwen/Qwen3-VL-2B-Instruct)
Finetuning method: LoRA adapters (SFT-style finetuning)
Tooling: Unsloth + TRL
Primary dataset: Kushtrim/bujku_vl_ocr (page image + Albanian transcription)
- Local snapshot used during development contains 34 000 images (train split).
- Training instruction: Transcribe the text in this image.

Practical defaults used by the trainer scripts in this folder (may vary by run):

max_length: 2048
learning rate: 2e-4
warmup ratio: 0.03
LoRA: r=16, alpha=16, dropout 0.0

Usage

🤗 Transformers (recommended)

Qwen3-VL support is in recent transformers. If you hit import errors, install from source:

pip install git+https://github.com/huggingface/transformers

import torch
from transformers import Qwen3VLForConditionalGeneration, AutoProcessor
from peft import PeftModel

BASE_ID = "Qwen/Qwen3-VL-2B-Instruct"          # <-- the real base model
ADAPTER_ID = "Kushtrim/Qwen3-VL-2B-Instruct-Shqip"

model = Qwen3VLForConditionalGeneration.from_pretrained(
    BASE_ID,
    torch_dtype="auto",
    device_map="auto",
    trust_remote_code=True,
)

model = PeftModel.from_pretrained(model, ADAPTER_ID, token=token)

# Optional (often nicer for inference): merge adapter into weights
model = model.merge_and_unload()

processor = AutoProcessor.from_pretrained(
    BASE_ID,
    trust_remote_code=True,
)

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "BU-19970125_34.png",
            },
            {"type": "text", "text": "Transcribe the text in this image."},
        ],
    }
]

# Preparation for inference
inputs = processor.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    return_dict=True,
    return_tensors="pt"
)
inputs = inputs.to(model.device)

# Inference: Generation of the output
generated_ids = model.generate(**inputs, max_new_tokens=2048)
generated_ids_trimmed = [
    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(output_text)

Limitations

Finetuning focus is OCR/document-style inputs; performance on general visual reasoning may differ from the base model.
OCR quality depends heavily on image quality (blur, skew, low resolution, heavy compression).
Historical newspapers may include OCR-hard typography, artifacts, and mixed-language snippets.

Development and attribution

Original Qwen3-VL architecture and weights: Qwen Team; fine-tuning-ready base distributed through unsloth/Qwen3-VL-2B-Instruct
Albanian OCR adaptation, dataset curation, fine-tuning, evaluation, packaging, and release: Kushtrim Visoka
Model card and ongoing maintenance: Kushtrim Visoka

Acknowledgements

This work builds on Qwen3-VL-2B-Instruct and the work of its original authors. The upstream architecture and base weights remain the work of their respective creators. This repository documents the task-specific adaptation and release work carried out by Kushtrim Visoka and does not claim authorship of the original model. Dataset creators and tool authors referenced elsewhere in this card should also be cited according to their licenses and documentation.

Citation

If you use this fine-tuned model, please cite this repository and the original upstream model.

@misc{visoka_qwen3_vl_2b_instruct_shqip_2026,
  author       = {Visoka, Kushtrim},
  title        = {Qwen3-VL 2B Instruct Shqip},
  year         = {2026},
  publisher    = {Hugging Face},
  url          = {https://huggingface.co/Kushtrim/Qwen3-VL-2B-Instruct-Shqip},
  note         = {Fine-tuned derivative of Qwen3-VL-2B-Instruct}
}