1 posts 0 posts

Hugging Face

Models, datasets, and tooling from the Hugging Face ecosystem.

NVIDIA cut Qwen3.6-35B 3×. Accuracy barely moved.
Hugging Face News & Releases Dev Tools & SDK Changelogs

NVIDIA cut Qwen3.6-35B 3×. Accuracy barely moved.

NVIDIA's NVFP4 Qwen3.6-35B checkpoint on HuggingFace: 3.06× memory reduction, <1% accuracy loss, Blackwell-native, vLLM flags included.

Creeta

이 섹션에 아직 한국어 글이 없습니다.

AI developer tools and ecosystem news for developers and technical founders

Featured posts

Tags

News & Releases News Dev Tools & SDK Changelogs Google / Gemini Claude / Anthropic OpenAI / Codex Model & API Releases Funding, Strategy & Policy MCP Protocols & Ecosystem Tutorial Daily How-To Build & Learn

Sign up for insights and ideas

Subscribe for the latest news, stories, tips, and updates.

Subscribe