AIAny
AI Model2026
Icon for item

Qwable-v1

Open-weights agentic coding model that layers Claude Fable‑5 tool‑use SFT onto a reasoning‑distilled Qwen3.6 base; emits <tool_use> XML for file edits, shell commands and reads when prompted as an agent. Designed for agentic coding workflows; AGPL‑3.0 licensed.

Introduction

Oops! Something went wrong

[next-mdx-remote-client] error compiling MDX: Expected a closing tag for `<tool_use>` (1:495-1:505) before the end of `paragraph` > 1 | Qwable‑v1 matters because it delivers an open‑weights path to agentic, tool‑oriented coding workflows at a time when the original Fable‑5 preview traces are no longer broadly available. Its core insight is a chained‑distill recipe: preserve Claude Opus 4.7's explicit chain‑of‑thought prior for reasoning, then add a narrow supervised fine‑tune of Claude Fable‑5 tool‑use traces to teach XML tool‑call behavior — producing a model that "thinks" with `<think>`…`</think>` blocks and "acts" with <tool_use> XML when framed as an agent. | ^ 2 | 3 | ## Key Capabilities More information: https://mdxjs.com/docs/troubleshooting-mdx

Information

More Items

Hugging Face
AI Model2026

Provides Q4_K_M GGUF weights for running Nemotron 3.5 Bolt E4B locally, with up to 64K-token context and support for multi-turn tool use.

Hugging Face
AI Model2026

Handles text, images, video, and audio in one model, then responds in text, speech, or both. Its 2.17B parameters and local-inference options target multimodal applications on edge devices.

Hugging Face
AI Model2025

Converts Chinese and English documents and PDFs into text and structured content, including tables, formulas, charts, and extracted fields. It is designed to handle real-world inputs such as scans and photographs.