Hackernews posts about Llama 405B

1. 01
   

   newShow HN: Fast and Cheap Llama-405Bcentml.ai

   ▲ 4akbarnur726ddiscusssavesaved
2. 02
   

   newLlama 3.1 405B now runs at 969 tokens/s on Cerebras Inferencecerebras.ai

   ▲ 427benchmarkist712d💬 156savesaved
3. 03
   

   newHuggingFace - Tencent launches Hunyuan Large which outperforms Llama 3.1 405Bhuggingface.co

   ▲ 23janik-io725d💬 1savesaved
4. 04
   

   newRunning Llama 3.1 405Ba11ce.com

   ▲ 4a11ce64ddiscusssavesaved
5. 05
   

   newVakgpt: Open-Source Chat Wrapper for Rapid AI Prototyping

   ▲ 1krishna-vakx521ddiscusssavesaved
6. 06
   

   newAllenAI Tulu 3 405B available for chat and download

   ▲ 12soundworlds635ddiscusssavesaved
7. 07
   

   newCerebras achieves 2,500T/s on Llama 4 Maverick (400B)www.cerebras.ai

   ▲ 93ByteAtATime519d💬 93savesaved
8. 08
   

   newShow HN: 1k desktop beats vendor sparse library 474× on Mistral-7Brolv.ai

   ▲ 1heggenhougen229d💬 1savesaved
9. 09
   

   newShow HN: ZSE – Open-source LLM inference engine with 3.9s cold startsgithub.com

   ▲ 58zyoralabs248d💬 9savesaved
10. 10
    

    newShow HN: OS Megakernel that match M5 Max Tok/w at 2x the Throughput on RTX 3090github.com

    ▲ 6GreenGames206d💬 1savesaved

· edit