The Rio 3.5 LLM, which briefly topped open‑source leaderboards, is shown to be a model‑merge product composed of roughly 60% Nex N2 Pro and 40% Alibaba's Qwen 3.5, with weight‑tensor analysis and prompt‑behavior tests confirming the claim.
A recent Artificial Analysis report finds that the 27‑billion‑parameter Qwen 3.5 and 31‑billion‑parameter Gemma 4 models achieve Intelligence Index scores comparable to GPT‑5, and the article details their benchmark results, multimodal capabilities, deployment on a single NVIDIA H100, and provides one‑click notebook tutorials for several open‑source LLMs.
This guide shows how to replace Anthropic's API by running a local Qwen 3.5 model with llama.cpp, configuring Claude Code via ANTHROPIC_BASE_URL, and includes hardware checks, build steps, model download, server launch, speed‑fix tips, and usage instructions for secure, cost‑free development.
On Chinese New Year's Eve, Alibaba's Qwen 3.5 open‑source model—featuring a 397 billion‑parameter backbone with a 17 billion‑parameter active set, hybrid linear attention, and sparse MoE—was released under Apache 2.0, delivering 8.6‑19× faster inference, top‑tier agent, code and multimodal scores, and rapid integration across major AI platforms.
Qwen 3.5, an open‑source 397B‑parameter model that activates only 17B parameters, uses a hybrid MoE‑Gated Delta architecture, offers native multimodal support and a default chain‑of‑thought mode, and achieves benchmark scores comparable to GPT‑5.2, Claude 4.5 Opus and Gemini 3 Pro across code, math, agent and vision tasks.
The LMSYS Chatbot Arena now shows Qwen 3.5 (codenamed Karp-001/002) alongside ByteDance's Pisces‑llm models and DeepSeek‑V4, with new Transformers configs and hints of an Active‑3B MoE architecture, suggesting a fresh wave of flagship large language models arriving for the Spring Festival.
