afgod1079/albedo-qwen3.6-35b-re1-cp100
The Qwen3.6-35B-A3B model by Qwen is a 35.1 billion parameter causal language model with a vision encoder, featuring 3 billion activated parameters and a native context length of 262,144 tokens, extensible up to 1,010,000 tokens. It is specifically optimized for agentic coding, enhancing frontend workflows and repository-level reasoning, and introduces 'Thinking Preservation' to streamline iterative development by retaining reasoning context from historical messages. This model excels in complex coding tasks and multimodal understanding, including image and video inputs.
Loading preview...
Qwen3.6-35B-A3B: Agentic Coding and Multimodal LLM
Qwen3.6-35B-A3B is a 35.1 billion parameter causal language model developed by Qwen, featuring a vision encoder and a native context length of 262,144 tokens, extensible to over 1 million tokens. This model introduces significant advancements in agentic coding and reasoning preservation, building upon the Qwen3.5 series.
Key Capabilities
- Enhanced Agentic Coding: Excels in frontend workflows and repository-level reasoning, offering improved fluency and precision for developers.
- Thinking Preservation: Features an option to retain reasoning context from historical messages, which streamlines iterative development and can reduce overhead by minimizing redundant reasoning.
- Multimodal Understanding: Supports both image and video inputs, making it suitable for a wide range of visual question answering and understanding tasks.
- Extended Context Window: Natively handles up to 262,144 tokens, with support for up to 1,010,000 tokens using YaRN scaling techniques, beneficial for ultra-long texts.
- Robust Performance: Demonstrates strong benchmark results across various categories, including Coding Agent, General Agent, Knowledge, STEM & Reasoning, and Vision Language tasks.
Good For
- Developers requiring advanced coding assistance: Particularly for agentic coding scenarios, frontend development, and complex repository analysis.
- Applications needing persistent reasoning: Ideal for iterative development where maintaining context across multiple interactions is crucial.
- Multimodal AI applications: Suitable for tasks involving image and video analysis, such as visual question answering and document understanding.
- High-throughput inference: Compatible with optimized inference frameworks like SGLang, vLLM, and KTransformers for efficient deployment.