Hackernews posts about LLaMa3.1

1. 01
   

   newLongwriter – Increase llama3.1 output to 10k wordsgithub.com

   ▲ 154taikon728d💬 29savesaved
2. 02
   

   newCerebras Inference now 3x faster: Llama3.1-70B breaks 2,100 tokens/scerebras.ai

   ▲ 147campers710d💬 84savesaved
3. 03
   

   newCognitivecomputations/Dolphin3.0-Llama3.1-8B uncensoredhuggingface.co

   ▲ 1simonpure637ddiscusssavesaved
4. 04
   

   newDistilling Llama3.1 8B into 1B in torchtunepytorch.org

   ▲ 1tosh664ddiscusssavesaved
5. 05
   

   newAsk HN: What's Your Useful Local LLM Stack?

   ▲ 91Olshansky447d💬 54savesaved
6. 06
   

   newShow HN: Musoq – Query Anything with SQL Syntax (Git, C#, CSV, Can DBC)github.com

   ▲ 56Puchaczov655d💬 15savesaved
7. 07
   

   newShow HN: How clanker are you? A reverse Turing testhowclankerareyou.com

   ▲ 11niklio93d💬 11savesaved
8. 08
   

   newShow HN: LLM-use – cost-effective LLM orchestrator for agents

   ▲ 2justvugg228d💬 1savesaved
9. 09
   

   newShow HN: EasyMemory – 100% local memory layer and MCP for LLMs

   ▲ 2justvugg228ddiscusssavesaved
10. 10
    

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

    ▲ 2justvugg240ddiscusssavesaved
11. 11
    

    newShow HN: Axiom – Open-source AI research agent that runs locally (C#, Ollama)github.com

    ▲ 1HexDynamics237ddiscusssavesaved
12. 12
    

    newShow HN: LLM-use – orchestrate LLMs for AI agents like OpenClaw, cut costs

    ▲ 1justvugg237ddiscusssavesaved
13. 13
    

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

    ▲ 1Mesterniz672ddiscusssavesaved

· edit