AirLLM runs 70B large language models on a single 4GB GPU without quantization, distillation or pruning. 405B Llama 3.1 on 8GB, DeepSeek-V3 671B on ~12GB.
Cross-referenced across 55 tracked directories
#8856
Popularity Rank
1 / 55
Listed In
Emerging
Adoption Stage
11/17/2023
First Seen
Recently added to the ecosystem
Unclecode
🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & scraper
ekuttan
Claude Code skill that generates structured product knowledge bases from codebase scanning