Hackernews posts about Llama-3.1 70B

1. 01
   

   newShow HN: Llama 3.1 70B on a single RTX 3090 via NVMe-to-GPU bypassing the CPUgithub.com

   ▲ 395xaskasdf251d💬 101savesaved
2. 02
   

   newFree Qwen 2.5, Llama Nemotron, OpenBioLLM, Gemini Exp 1121, and LearnLM 1.5 Pro

   ▲ 2gizai707d💬 1savesaved
3. 03
   

   newShow HN: LLM-use – Open-source tool to route and orchestrate multi-LLM tasks

   ▲ 2justvugg266ddiscusssavesaved
4. 04
   

   newShow HN: Which LLM Finds Obscure Knife-Brand URLs Cheapest? (8-Model Benchmark)new.knife.day

   ▲ 2p-s-v514ddiscusssavesaved
5. 05
   

   newShow HN: I Used Llama-70B Logprobs for Better, Cheaper and Faster Chunkinggithub.com

   ▲ 1ghita_695ddiscusssavesaved
6. 06
   

   newShow HN: Unfat, a library to easily train and distill LoRAs for LLMsgithub.com

   ▲ 6reissbaker603ddiscusssavesaved
7. 07
   

   newShow HN: Sleeping LLM – A language model that remembers by sleepinggithub.com

   ▲ 2vbaranov87247ddiscusssavesaved
8. 08
   

   newVakgpt: Open-Source Chat Wrapper for Rapid AI Prototyping

   ▲ 1krishna-vakx521ddiscusssavesaved
9. 09
   

   newShow HN: LLM Fine-tuning platform with integrated data labelingubiai.tools

   ▲ 1Mesterniz698ddiscusssavesaved
10. 10
    

    newAsk HN: How is GPU power draw measured at scale?

    ▲ 6anax32127d💬 2savesaved

· edit