Instructions to use MuhammedKsee/Qwen3.5-9B-Instruct-Turca-TurkishLLM-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MuhammedKsee/Qwen3.5-9B-Instruct-Turca-TurkishLLM-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="MuhammedKsee/Qwen3.5-9B-Instruct-Turca-TurkishLLM-GGUF",
	filename="Qwen3.5-9B-InstrucTurca-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use MuhammedKsee/Qwen3.5-9B-Instruct-Turca-TurkishLLM-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf MuhammedKsee/Qwen3.5-9B-Instruct-Turca-TurkishLLM-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf MuhammedKsee/Qwen3.5-9B-Instruct-Turca-TurkishLLM-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf MuhammedKsee/Qwen3.5-9B-Instruct-Turca-TurkishLLM-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf MuhammedKsee/Qwen3.5-9B-Instruct-Turca-TurkishLLM-GGUF: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 MuhammedKsee/Qwen3.5-9B-Instruct-Turca-TurkishLLM-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf MuhammedKsee/Qwen3.5-9B-Instruct-Turca-TurkishLLM-GGUF: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 MuhammedKsee/Qwen3.5-9B-Instruct-Turca-TurkishLLM-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf MuhammedKsee/Qwen3.5-9B-Instruct-Turca-TurkishLLM-GGUF:Q4_K_M

Use Docker

docker model run hf.co/MuhammedKsee/Qwen3.5-9B-Instruct-Turca-TurkishLLM-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use MuhammedKsee/Qwen3.5-9B-Instruct-Turca-TurkishLLM-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MuhammedKsee/Qwen3.5-9B-Instruct-Turca-TurkishLLM-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": "MuhammedKsee/Qwen3.5-9B-Instruct-Turca-TurkishLLM-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MuhammedKsee/Qwen3.5-9B-Instruct-Turca-TurkishLLM-GGUF:Q4_K_M

Ollama
How to use MuhammedKsee/Qwen3.5-9B-Instruct-Turca-TurkishLLM-GGUF with Ollama:
```
ollama run hf.co/MuhammedKsee/Qwen3.5-9B-Instruct-Turca-TurkishLLM-GGUF:Q4_K_M
```

Unsloth Studio new

How to use MuhammedKsee/Qwen3.5-9B-Instruct-Turca-TurkishLLM-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 MuhammedKsee/Qwen3.5-9B-Instruct-Turca-TurkishLLM-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 MuhammedKsee/Qwen3.5-9B-Instruct-Turca-TurkishLLM-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for MuhammedKsee/Qwen3.5-9B-Instruct-Turca-TurkishLLM-GGUF to start chatting

Pi new

How to use MuhammedKsee/Qwen3.5-9B-Instruct-Turca-TurkishLLM-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf MuhammedKsee/Qwen3.5-9B-Instruct-Turca-TurkishLLM-GGUF:Q4_K_M

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": "MuhammedKsee/Qwen3.5-9B-Instruct-Turca-TurkishLLM-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use MuhammedKsee/Qwen3.5-9B-Instruct-Turca-TurkishLLM-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 MuhammedKsee/Qwen3.5-9B-Instruct-Turca-TurkishLLM-GGUF: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 MuhammedKsee/Qwen3.5-9B-Instruct-Turca-TurkishLLM-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use MuhammedKsee/Qwen3.5-9B-Instruct-Turca-TurkishLLM-GGUF with Docker Model Runner:
```
docker model run hf.co/MuhammedKsee/Qwen3.5-9B-Instruct-Turca-TurkishLLM-GGUF:Q4_K_M
```

Lemonade

How to use MuhammedKsee/Qwen3.5-9B-Instruct-Turca-TurkishLLM-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull MuhammedKsee/Qwen3.5-9B-Instruct-Turca-TurkishLLM-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.5-9B-Instruct-Turca-TurkishLLM-GGUF-Q4_K_M

List all available models

lemonade list

Qwen3.5-9B-Instruct-Turca-TurkishLLM — GGUF 🇹🇷⚡

Quantized GGUF versions of muhammedksee/Qwen3.5-9B-Instruct-Turca-TurkishLLM for local inference on consumer hardware — no data center GPU required.

Looking for the full-precision model? Training details, hyperparameters, and benchmark results are in the base repository.

Developer

Field	Value
Developer	Muhammed Köse
LinkedIn	muhammedksee
GitHub	muhammedksee
Base Model (BF16)	muhammedksee/Qwen3.5-9B-Instruct-Turca-TurkishLLM
License	Apache 2.0

Available Quantizations

File	Quant	Size	RAM Required	Notes
`Qwen3.5-9B-InstrucTurca-Q4_K_M.gguf`	Q4_K_M	~5.5–6.5 GB	8 GB min / 16 GB recommended	Recommended — best balance of quality and memory

Why Q4_K_M?

Running a 9B-parameter model at full precision (BF16) requires a data center-grade GPU. GGUF quantization compresses the model weights with minimal quality loss, making it fit in consumer RAM and VRAM.

Q4_K_M retains nearly all of the model's Turkish language understanding and reasoning capability while cutting memory usage roughly in half. It is the community standard for everyday use and local RAG pipelines.

System Requirements

Config	RAM / VRAM
Minimum (CPU only)	8 GB RAM
Recommended	16 GB RAM or VRAM
GPU acceleration	Apple Silicon (M1/M2/M3) or NVIDIA RTX 3050+

GPU offloading is optional but strongly recommended — with a supported GPU you can reach tens of tokens/second instead of single digits on CPU.

Quick Start

Option 1 — Ollama

Preferred for terminal access or running a local API server.

Step 1. Download the GGUF file.

Step 2. Create a file named Modelfile (no extension) in the same directory:

FROM ./Qwen3.5-9B-InstrucTurca-Q4_K_M.gguf

TEMPLATE """<|im_start|>system
{{ .System }}<|im_end|>
<|im_start|>user
{{ .Prompt }}<|im_end|>
<|im_start|>assistant
"""

SYSTEM """Sen yardımcı, dürüst ve zararsız bir Türkçe yapay zeka asistanısın."""

Step 3. Build and run:

ollama create turca-9b -f Modelfile
ollama run turca-9b

Option 2 — Python / llama-cpp-python

For integrating the model into your own Python projects (local RAG, automation agents, etc.).

pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama(
    model_path="./Qwen3.5-9B-InstrucTurca-Q4_K_M.gguf",
    n_ctx=4096,       # context window
    n_threads=8,      # CPU threads — match your core count
    n_gpu_layers=35   # increase if you have more VRAM
)

system_prompt = "Sen uzman bir yazılım mühendisi ve yapay zeka asistanısın."
user_prompt   = "Python'da liste üreteçleri (list comprehensions) nedir? Kısa bir örnek ver."

prompt = (
    f"<|im_start|>system\n{system_prompt}<|im_end|>\n"
    f"<|im_start|>user\n{user_prompt}<|im_end|>\n"
    f"<|im_start|>assistant\n"
)

output = llm(
    prompt,
    max_tokens=512,
    temperature=0.7,
    top_p=0.9,
    stop=["<|im_end|>"]
)

print(output["choices"][0]["text"])

Prompt Format (ChatML)

This model uses the standard Qwen ChatML format. Always follow this template when calling the model directly — deviating from it increases hallucination risk and degrades output quality.

<|im_start|>system
Sen Türkçe konuşan, yardımcı bir asistansın.<|im_end|>
<|im_start|>user
Merhaba, nasılsın?<|im_end|>
<|im_start|>assistant

The system prompt can be in Turkish or English. Turkish system prompts are recommended as they better align with the fine-tuning distribution.

Intended Use

Use Case	Verdict
Turkish conversational assistant (local)	✅ Primary use case
Local RAG over Turkish documents	✅ Recommended
Offline / privacy-sensitive deployment	✅ Fully local, no data sent anywhere
Production enterprise (high-stakes)	⚠️ Test against your workload first
Complex coding / advanced reasoning	⚠️ Full-precision BF16 model may perform better

Limitations

Quantization loss. Q4_K_M is a 4-bit mathematical compression. While the quality difference is minimal for most tasks, very fine-grained Turkish grammar nuances or highly complex math/coding problems may show slight degradation compared to the BF16 base model.

No benchmark results yet. Formal evaluations (MT-Bench TR, MMLU-TR, base model comparison) are in progress. See the base repository for updates.

SFT only. No DPO or RLHF alignment stage was applied to the base model. Responses may occasionally be less reliable than preference-aligned models.

Test on your specific workload before production deployment.

Related Resources

Resource	Link
Base model (BF16)	muhammedksee/Qwen3.5-9B-Instruct-Turca-TurkishLLM
Training dataset	turkish-nlp-suite/InstrucTurca
Original base model	Qwen/Qwen3.5-9B
Ollama	ollama.com

Citation

@misc{kose2025qwen35turca_gguf,
  author    = {Muhammed Köse},
  title     = {Qwen3.5-9B-Instruct-Turca-TurkishLLM GGUF},
  year      = {2026},
  publisher = {Hugging Face},
  url       = {https://huggingface.co/muhammedksee/Qwen3.5-9B-Instruct-Turca-TurkishLLM-GGUF}
}

Downloads last month: 302

GGUF

Model size

9B params

Architecture

qwen35

Hardware compatibility

4-bit