Next2 0.8B is a highly optimized, 800-million parameter language model built on the cutting-edge Qwen 3.5 architecture. Carefully fine-tuned and developed in Türkiye, it is designed to deliver astonishing reasoning capabilities in a form factor small enough to run on local laptops, edge devices, and mobile environments.
Don't let the size fool you. Thanks to extensive instruction tuning and enhanced Thinking Mode datasets, Next2 0.8B punches significantly above its weight class. It introduces localized cultural nuances for Turkish users while maintaining top-tier English proficiency. It’s built to think, reason logically, and provide structured answers efficiently.
⚡ Highlights
🇹🇷 Developed & Fine-Tuned in Türkiye: Specially optimized for rich Turkish syntax and logical flows.
🧠 Native Thinking Mode: Capable of chain-of-thought (CoT) reasoning for complex problem-solving.
📱 Edge & Mobile Ready: At just 0.8B parameters, it runs blazingly fast on CPUs, low-end GPUs, and edge hardware.
⚡ Enhanced Over Base: Noticeably improved mathematical reasoning and instruction following compared to standard 1B models.
📊 Benchmark Performance
We tested Next2 0.8B against its base model and other models in the sub-2B category. Through careful dataset curation and SFT (Supervised Fine-Tuning) in Türkiye, it shows a tangible improvement in logical reasoning and contextual understanding.
Model
MMLU (5-shot)
IFEval
GSM8K (Math)
Context Limit
🚀 Next2 0.8B (Thinking)
52.1%
55.8%
67.4%
32K+
Base Qwen3.5-0.8B
48.5%
52.1%
62.2%
262K
Llama-3.2-1B
49.3%
50.2%
60.5%
128K
* Scores represent generalized task performance. Next2 0.8B shows a distinct advantage in reasoning (GSM8K) and instruction following (IFEval) due to our proprietary fine-tuning pipelines.
🚀 Quickstart & Usage
You can easily run Next2 0.8B on almost any machine with Python installed. Because of its size, device_map="auto" will comfortably map it to memory without breaking a sweat.
python
1from transformers import AutoTokenizer, AutoModelForCausalLM, AutoProcessor
2from PIL import Image
3import torch
45model_id ="thelamapi/next2-0.8b"67model = AutoModelForCausalLM.from_pretrained(model_id)8processor = AutoProcessor.from_pretrained(model_id)# For vision.9tokenizer = AutoTokenizer.from_pretrained(model_id)101112# Create a message in chat format13messages =[14{"role":"system","content":[{"type":"text","text":"You are Next2, a smart and concise AI assistant trained by Lamapi. Always respond in the user's language. Proudly made in Turkey."}]},1516{17"role":"user","content":[18{"type":"text","text":"Write a highly optimized Rust function to calculate the Fibonacci sequence using memoization"}19]20}21]2223# Prepare input with Tokenizer24prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=False)25inputs = processor(text=prompt, return_tensors="pt")2627# Remove 'mm_token_type_ids' if it's not needed for text-only generation28if"mm_token_type_ids"in inputs:29del inputs["mm_token_type_ids"]303132# Output from the model33output = model.generate(**inputs, do_sample=True, temperature=0.7, max_new_tokens=128)34print(tokenizer.decode(output[0], skip_special_tokens=True))
Ultra-lightweight (Can run on 2GB RAM / Edge GPUs)
Format
FP16 natively, Quantization (GGUF/AWQ) recommended for mobile
🎯 Ideal Use Cases
Since it is compact yet surprisingly capable, Next2 0.8B is perfect for:
🔋 On-Device AI: Running locally on smartphones, Raspberry Pi, or older laptops without internet.
🤖 NPC & Gaming AI: Fast, low-latency dialogue generation for video games.
📝 Text Summarization & Extraction: Processing documents locally to maintain high data privacy.
🇹🇷 Turkish NLP Tasks: Fast classification, sentiment analysis, and daily conversational AI in Turkish.
📄 License & Open Source
Licensed under the MIT License. We believe in democratizing AI, making smart, reasoning-capable models accessible to everyone. Feel free to use it in commercial apps, academic research, or personal projects!
