Instructions to use umitaksoylu/lsda-3b-turkish-dev-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use umitaksoylu/lsda-3b-turkish-dev-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 umitaksoylu/lsda-3b-turkish-dev-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf umitaksoylu/lsda-3b-turkish-dev-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf umitaksoylu/lsda-3b-turkish-dev-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf umitaksoylu/lsda-3b-turkish-dev-GGUF:F16

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 umitaksoylu/lsda-3b-turkish-dev-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf umitaksoylu/lsda-3b-turkish-dev-GGUF:F16

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 umitaksoylu/lsda-3b-turkish-dev-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf umitaksoylu/lsda-3b-turkish-dev-GGUF:F16

Use Docker

docker model run hf.co/umitaksoylu/lsda-3b-turkish-dev-GGUF:F16

LM Studio
Jan

vLLM

How to use umitaksoylu/lsda-3b-turkish-dev-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "umitaksoylu/lsda-3b-turkish-dev-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "umitaksoylu/lsda-3b-turkish-dev-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/umitaksoylu/lsda-3b-turkish-dev-GGUF:F16

Ollama
How to use umitaksoylu/lsda-3b-turkish-dev-GGUF with Ollama:
```
ollama run hf.co/umitaksoylu/lsda-3b-turkish-dev-GGUF:F16
```
Unsloth Desktop

How to use umitaksoylu/lsda-3b-turkish-dev-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf umitaksoylu/lsda-3b-turkish-dev-GGUF:F16

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": "umitaksoylu/lsda-3b-turkish-dev-GGUF:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use umitaksoylu/lsda-3b-turkish-dev-GGUF with Docker Model Runner:
```
docker model run hf.co/umitaksoylu/lsda-3b-turkish-dev-GGUF:F16
```

Lemonade

How to use umitaksoylu/lsda-3b-turkish-dev-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull umitaksoylu/lsda-3b-turkish-dev-GGUF:F16

Run and chat with the model

lemonade run user.lsda-3b-turkish-dev-GGUF-F16

List all available models

lemonade list

Hermes Agent

How to use umitaksoylu/lsda-3b-turkish-dev-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf umitaksoylu/lsda-3b-turkish-dev-GGUF:F16

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 umitaksoylu/lsda-3b-turkish-dev-GGUF:F16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use umitaksoylu/lsda-3b-turkish-dev-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf umitaksoylu/lsda-3b-turkish-dev-GGUF:F16

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 "umitaksoylu/lsda-3b-turkish-dev-GGUF:F16" \
  --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"

LSDA 3B Turkish Dev - GGUF Versions

This repository contains GGUF quantized versions of umitaksoylu/lsda-3b-turkish-dev, compiled using llama.cpp.

LSDA-3B-Turkish-Dev is a high-performance 3B parameter LLM (based on Qwen2.5 Architecture) specifically trained for modern full-stack software development with a deep focus on C#, SQL, and React. LSDA Supports English & Turkish languages.

📦 Available Files & Specs

File Name	Quant Method	File Size	Recommended RAM/VRAM	Primary Use Case
`lsda-3b-turkish-dev-Q4_K_M.gguf`	Q4_K_M	~2.1 GB	≥ 4 GB	Mobile devices (iOS/Android), low VRAM GPUs (e.g. GTX 1650), or CPU-only local environments. Minimal quality degradation with optimal speed.
`lsda-3b-turkish-dev-F16.gguf`	FP16	~6.0 GB	≥ 8 GB	Uncompressed reference tests and evaluations on regular CPU's or Apple Silicon (Metal).

🛠️ Supported Inference Engines

You can run these GGUF weights across a wide variety of edge, mobile, and server engines:

llama.cpp (Native cross-platform execution)
Ollama (Local REST server & CLI)
MLC-LLM (Cross-platform GPU acceleration)
ExecuTorch (PyTorch native mobile engine)
MediaPipe GenAI (On-device deployment)
RKNN-LLM (Rockchip NPU acceleration)
TensorRT-LLM (NVIDIA Edge/Server acceleration)

📱 Device Compatibility & Benchmarks ("The Developer in Your Pocket")

Thanks to GGUF and 4-bit quantization support, LSDA-3B can run locally across a wide range of hardware, including smartphones, tablets, edge AI boards, and low-power Mini PCs.

🍎 Apple Ecosystem (Metal / Apple Neural Engine)

Device Series	Memory (RAM)	Expected Experience / Performance
iPhone 16 / 16 Plus / Pro / Pro Max	8 GB	Ideal local on-device experience
iPhone 15 Pro / 15 Pro Max	8 GB	Accelerated by Apple A17 Pro ANE hardware
iPhone 15, 14 (Base/Pro), 13 Pro	6 GB	Stable & smooth performance with 4-bit (Q4) models
iPhone 13 (Base) / 13 Mini	4 GB	Lightweight local usage with 4-bit (Q4) or aggressive quants
iPad Pro & iPad Air (M1 / M2 / M4)	8 GB – 16 GB	Desktop-grade local inference speeds
iPad Mini / iPad (A15 / A16 / A17)	4 GB – 6 GB	Portable, lightweight local coding assistant

🤖 Android Devices (Min. 6 GB, Recommended 8 GB+ RAM)

Chipset Architecture	Example Devices / Hardware	Performance
Qualcomm Snapdragon 8 Gen 1 / 2 / 3 / 8 Elite	Galaxy S23/S24, Xiaomi 13/14 (Hexagon NPU & Adreno GPU)	25 – 45 tok/s
Qualcomm Snapdragon 7+ Gen 2 / 7 Gen 3	Upper mid-range Android smartphones	Fluid local inference
Samsung Exynos 2400 / 2200 / 1480	AMD RDNA-based Xclipse GPU & NPU acceleration	~20 – 35 tok/s
Huawei Kirin 9000 / 9000s / 9010	Huawei Mate 60, Pura 70 (DaVinci NPU)	Full hardware support
MediaTek Dimensity 9200 / 9300 / 9400 & 8300	Flagship/Sub-flagship devices (APU NPU architecture)	High power efficiency

🤖 Embedded, Robotics & Edge AI

Platform / Hardware	Specs / Acceleration	Inference Speed
NVIDIA Jetson Orin Nano (4GB / 8GB)	TensorRT-LLM & llama.cpp support	~30+ tok/s
NVIDIA Jetson Orin NX / AGX Orin	Industrial automation & real-time robotics	High throughput
Raspberry Pi 5 (4GB / 8GB)	CPU execution via llama.cpp / Ollama (Q4_K_M)	~5 – 8 tok/s
Orange Pi 5 / 5+ (RK3588)	6 TOPS NPU acceleration via RKNN-LLM	~12 – 18 tok/s
Intel N100 / N97 / Core i3-N305	6W–15W Ultra Low-Power x86 Mini PCs / IoT Gateways	~10 – 15 tok/s

🚀 Quick Start

1. Running via `llama.cpp` CLI

# Download the quantized GGUF file
huggingface-cli download umitaksoylu/lsda-3b-turkish-dev-GGUF lsda-3b-turkish-dev-Q4_K_M.gguf --local-dir .

# Run with Qwen 2.5 chat template
./llama-cli -m lsda-3b-turkish-dev-Q4_K_M.gguf \
  --chat-template qwen2 \
  -p "Write a C# DTO class and a corresponding React interface for a User Profile." \
  -n 512

Downloads last month: 146

GGUF

Model size

3B params

Architecture

qwen2

Hardware compatibility

4-bit

16-bit

Model tree for umitaksoylu/lsda-3b-turkish-dev-GGUF

Base model

Qwen/Qwen2.5-3B

Finetuned

umitaksoylu/lsda-3b-turkish-dev

Quantized

(1)

this model

LSDA 3B Turkish Dev - GGUF Versions

📦 Available Files & Specs

🛠️ Supported Inference Engines

📱 Device Compatibility & Benchmarks ("The Developer in Your Pocket")

🍎 Apple Ecosystem (Metal / Apple Neural Engine)

🤖 Android Devices (Min. 6 GB, Recommended 8 GB+ RAM)

🤖 Embedded, Robotics & Edge AI

🚀 Quick Start

1. Running via llama.cpp CLI

Model tree for umitaksoylu/lsda-3b-turkish-dev-GGUF

1. Running via `llama.cpp` CLI