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 a drop-in checkpoint of DeepSeek-V4.1-Flash with weight-level abliteration that removes safety guardrails to produce uncensored outputs; preserves vision, MoE routing, 1M-token context and native FP8 quantization. Intended for advanced self-hosted deployment; requires large NVLink GPU domains and careful serving setup.

Hugging Face
AI Model2026

A reasoning‑efficient fine-tune of Qwen3.8-27B that penalizes overthinking tokens to shorten internal reasoning traces — about 58.3% fewer thinking tokens with <1% accuracy loss and ~1.95× speedup; designed for long-context, multimodal and quantized deployments.

Hugging Face
AI Model2026

Open-weights preview checkpoint for a multimodal reasoning model that generates text from text and image/video inputs, exposes adjustable reasoning effort and tool-calling, and supports an extended 262,144-token context for long-horizon tasks and agent-style workflows.