Next2-Air (2B)
Türkiye’s Fastest Lightweight Multimodal & Reasoning AI
<think>) to logically deduce answers before speaking.| Benchmark | Next2-Air (2B) | Qwen 3.5 (2B) | Gemma-2 (2B) | Llama-3.2 (3B) |
|---|---|---|---|---|
| MMLU-Pro (Thinking) | 68.2% | 66.5% | 54.1% | 68.4% |
| MMLU-Redux | 82.1% | 79.6% | 75.3% | 79.5% |
| IFEval (Instruction) | 82.5% | 78.6% | 75.8% | 77.4% |
| TAU2-Bench (Agent) | 52.4% | 48.8% | -- | -- |
| Benchmark | Next2-Air (2B) | Base Qwen3.5-2B |
|---|---|---|
| MMMU (General VQA) | 66.5% | 64.2% |
| MathVision | 78.1% | 76.7% |
| OCRBench | 86.0% | 84.5% |
| VideoMME (w/ sub) | 77.8% | 75.6% |
* Enhanced scores in reasoning and OCR are a direct result of Lamapi's specialized bilingual finetuning pipeline focusing on edge-case logic and structural formatting.
--- ## 🚀 Quickstart & Usage **Next2-Air** is fully compatible with the Hugging Face `transformers` ecosystem and fast inference engines like `vLLM` and `SGLang`. Because it's a VLM, you can directly pass images into your prompts. ### Python (Transformers) Make sure you have `transformers`, `torch`, `torchvision`, and `pillow` installed. ```python from transformers import AutoTokenizer, AutoModelForCausalLM, AutoProcessor from PIL import Image import torch model_id = "thelamapi/next2-air" model = AutoModelForCausalLM.from_pretrained(model_id) processor = AutoProcessor.from_pretrained(model_id) # For vision. tokenizer = AutoTokenizer.from_pretrained(model_id) # Create a message in chat format messages = [ {"role": "system","content": [{"type": "text", "text": "You are Next2 Air, a smart and concise AI assistant trained by Lamapi. Always respond in the user's language. Proudly made in Turkey."}]}, { "role": "user","content": [ {"type": "text", "text": "Write a highly optimized Rust function to calculate the Fibonacci sequence using memoization"} ] } ] # Prepare input with Tokenizer prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=False) inputs = processor(text=prompt, return_tensors="pt") # Remove 'mm_token_type_ids' if it's not needed for text-only generation if "mm_token_type_ids" in inputs: del inputs["mm_token_type_ids"] # Output from the model output = model.generate(**inputs, do_sample=True, temperature=0.7, max_new_tokens=128) print(tokenizer.decode(output[0], skip_special_tokens=True)) ``` --- ## 🧩 Model Specifications | Attribute | Details | | :--- | :--- | | **Base Architecture** | Qwen 3.5 (Causal Language Model + Vision Encoder) | | **Parameters** | 2 Billion (Ultra-Lightweight) | | **Context Length** | 262,144 tokens natively | | **Hardware** | Optimized for Edge devices, MacBooks (MLX), Consumer GPUs, and low-VRAM environments. | | **Capabilities** | Text Generation, Image Understanding, OCR, Logic & Reasoning (CoT), Bilingual (TR/EN) | --- ## 🎯 Ideal Use Cases **Next2-Air** is the undisputed champion of local, fast inference tasks. It is perfect for: * 🔋 **Mobile & Edge AI:** Deploying smart assistants natively on smartphones or Raspberry Pi without relying on cloud APIs. * ⚡ **Real-Time OCR & Parsing:** Quickly scanning receipts, invoices, or UI screenshots to extract data in milliseconds. * 💬 **Fast Conversational Bots:** Providing instant, low-latency Turkish and English responses for customer service pipelines. * 🎮 **Gaming & NPC Logic:** Acting as a fast reasoning engine for dynamic in-game characters. --- ## 📄 License & Open Source Next2-Air is released under the **Apache 2.0 License**. We strongly believe in empowering developers, students, and enterprises with accessible, high-speed, reasoning-capable AI. --- ## 📞 Contact & Community * 📧 **Email:**[lamapicontact@gmail.com](mailto:lamapicontact@gmail.com) * 🤗 **HuggingFace:** [Lamapi](https://huggingface.co/Lamapi) * 💬 **Discord:** [Join the Lamapi Community](https://discord.gg/XgH4EpyPD2) ---Next2-Air — Hafif, Hızlı, Akıllı. Uç cihazlardan buluta, Türkiye'nin yeni nesil çevik yapay zekası. 🌬️