Open-weights agentic coding model Qwable-v1 released on Hugging Face

The "lordx64/Qwable-v1" model, an open-weights agentic coding model, has been released on Hugging Face. This model is a distillation of Qwen3.6-35B-A3B, incorporating reasoning traces from Claude Opus 4.7 and agentic tool-use behaviors from Claude Fable-5. It is designed to perform chained distillations, enabling explicit chains-of-thought and agent-like behavior with XML-formatted tool use for actions like file edits and shell commands. AI

IMPACT Enables developers to leverage an open-weights agentic coding model with explicit reasoning and tool-use capabilities.

RANK_REASON Release of an open-weights model with details on its training and capabilities. [lever_c_demoted from research: ic=1 ai=1.0]

Read on Hugging Face Trending Models →

• Claude Fable-5
• Claude Opus 4.7
• Docker
• Google Colab
• Hugging Face
• Kaggle
• lmsysorg
• lordx64/Qwable-v1
• OpenAI
• Qwen3.6-35B-A3B
• SGLang
• transformers
• vLLM

• model release
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →