Turkish-LLM-7B-Instruct

A Turkish-enhanced 7B language model fine-tuned from Mistral-7B-Instruct on curated Turkish instruction data.

Part of the Turkish LLM Family.

Highlights

• Lightweight - runs on consumer GPUs (8GB+ VRAM with quantization)
• GGUF available - Q4/Q5/Q8 quantizations
• Live demo - Try it on Spaces

Quick Start

With Ollama

ollama run hf.co/ogulcanaydogan/Turkish-LLM-7B-Instruct-GGUF:Q4_K_M

With Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("ogulcanaydogan/Turkish-LLM-7B-Instruct", torch_dtype="auto", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("ogulcanaydogan/Turkish-LLM-7B-Instruct")

messages = [{"role": "user", "content": "Turkiye'nin baskenti neresidir?"}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer([text], return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Turkish LLM Family

Model	Size	GGUF
Turkish-LLM-7B	7B	Download
Turkish-LLM-14B	14B	Download
Turkish-LLM-32B	32B	Download

Citation

@misc{aydogan2026turkishllm,
  title={Turkish LLM Family: Open-Source Turkish Language Models},
  author={Ogulcan Aydogan},
  year={2026},
  url={https://huggingface.co/collections/ogulcanaydogan/turkish-llm-family-69b303b4ef1c36caffca4e94}
}