Add 5 elite-tier foundation models to Section 2

- Qwen3 (27K stars) - Flagship dense/MoE models with hybrid thinking
- Qwen3.6 (3.2K stars) - Latest flagship with 1M context
- MiMo (2K stars) - 7B reasoning model surpassing DeepSeek R1
- MiMo-V2-Flash (1.3K stars) - 309B MoE with efficient inference
- Nemotron (1K stars) - NVIDIA's open models for agentic AI

All models are Apache 2.0 licensed with active development.

Author: alvinreal

README.md

@@ -226,7 +226,11 @@
 #### Large Language Models (Base + Chat)
 
 - **[RWKV-7 "Goose" (BlinkDL)](https://github.com/BlinkDL/RWKV-LM)** ![GitHub stars](https://img.shields.io/github/stars/BlinkDL/RWKV-LM?style=social) - Novel RNN architecture with transformer-level LLM performance. 100% attention-free, linear-time, constant-space (no kv-cache), infinite ctx_len. Linux Foundation AI project with runtime already deployed in Windows & Office.
-- **[Qwen3.6-Plus (Alibaba)](https://github.com/QwenLM/Qwen)** ![GitHub stars](https://img.shields.io/github/stars/QwenLM/Qwen?style=social) - Latest flagship series released April 2026 with 1M context window, agentic coding performance competitive with Claude 4.5 Opus, and enhanced multimodal capabilities.
+- **[Qwen3 (Alibaba)](https://github.com/QwenLM/Qwen3)** ![GitHub stars](https://img.shields.io/github/stars/QwenLM/Qwen3?style=social) - Flagship dense and MoE models with hybrid thinking modes (32B/235B). Apache 2.0 licensed with 128K context and superior agentic capabilities.
+- **[Qwen3.6 (Alibaba)](https://github.com/QwenLM/Qwen3.6)** ![GitHub stars](https://img.shields.io/github/stars/QwenLM/Qwen3.6?style=social) - Latest flagship series released April 2026 with 1M context window, agentic coding performance competitive with Claude 4.5 Opus, and enhanced multimodal capabilities.
+- **[MiMo (Xiaomi)](https://github.com/XiaomiMiMo/MiMo)** ![GitHub stars](https://img.shields.io/github/stars/XiaomiMiMo/MiMo?style=social) - 7B reasoning model trained from scratch with RL scaling that surpasses DeepSeek R1 on math and coding benchmarks. Apache 2.0 licensed.
+- **[MiMo-V2-Flash (Xiaomi)](https://github.com/XiaomiMiMo/MiMo-V2-Flash)** ![GitHub stars](https://img.shields.io/github/stars/XiaomiMiMo/MiMo-V2-Flash?style=social) - 309B MoE model (15B active) with hybrid attention and Multi-Token Prediction for efficient high-speed reasoning. Apache 2.0 licensed.
+- **[Nemotron (NVIDIA)](https://github.com/NVIDIA-NeMo/Nemotron)** ![GitHub stars](https://img.shields.io/github/stars/NVIDIA-NeMo/Nemotron?style=social) - Open and efficient models for agentic AI with training recipes, deployment guides, and use-case examples. Apache 2.0 licensed.
 - **[Gemma 4 (Google)](https://github.com/google-deepmind/gemma)** ![GitHub stars](https://img.shields.io/github/stars/google-deepmind/gemma?style=social) - Released April 2026 in four sizes (E2B, E4B, 26B MoE, 31B Dense). First major update in a year with Apache 2.0 license, complex logic, and agentic workflows.
 - **[Kimi K2 (Moonshot AI)](https://github.com/MoonshotAI/Kimi-K2)** ![GitHub stars](https://img.shields.io/github/stars/MoonshotAI/Kimi-K2?style=social) - State-of-the-art 1T parameter MoE model with 32B activated parameters and 128K context. Trained with Muon optimizer for exceptional reasoning and coding performance.
 - **[Kimi K2.5 (Moonshot AI)](https://github.com/MoonshotAI/Kimi-K2.5)** ![GitHub stars](https://img.shields.io/github/stars/MoonshotAI/Kimi-K2.5?style=social) - Frontier open-weight MoE model with 256K context, strong coding and reasoning performance, and native multimodal + tool-use support for agentic workflows.