PulseAugur
EN
LIVE 07:03:41
tool · [1 source] ·

Unsloth beta adds 2x faster inference, API calling, and MLX support

Unsloth has released version v0.1.405-beta, introducing significant performance enhancements and new features. The update includes up to 2x faster GGUF inference through MTP speculative decoding and adds API calling support for services like OpenAI and Anthropic, enabling features such as web search and code execution. Additionally, Unsloth now offers experimental MLX inference for Mac users and improved support for non-English languages, alongside various security and UI/UX improvements. AI

Summary written by gemini-2.5-flash-lite from 1 sources. How we write summaries →

IMPACT Accelerates local LLM inference and integration capabilities for developers.

RANK_REASON This is a software release for an AI tooling company, not a core model release from a frontier lab.

Read on Unsloth — Releases →

Unsloth beta adds 2x faster inference, API calling, and MLX support

COVERAGE [1]

  1. Unsloth — Releases TIER_1 · shimmyshimmer ·

    Qwen3.6 MTP and API / Connections

    <p>We've got lots of new updates. Please use the latest Unsloth <code>v0.1.405-beta</code>, not <code>v0.1.40-beta</code> which is older.</p> <ul> <li><strong>~2x faster GGUF inference</strong> with automatically enabled MTP</li> <li><a href="https://unsloth.ai/docs/integrations/…