Hackernews posts about Cerebras Inference

1. 01
   

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

   ▲ 427benchmarkist686d💬 156savesaved
2. 02
   

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

   ▲ 147campers710d💬 84savesaved
3. 03
   

   newUltrafast Frontier Inference – Cerebras Hot Chips 2026www.cerebras.ai

   ▲ 10rbanffy40ddiscusssavesaved
4. 04
   

   newCerebras Inference now runs Llama 3.1-70B at 2100 tokens/scerebras.ai

   ▲ 6cs-fan-101711ddiscusssavesaved
5. 05
   

   newHow Cerebras AI Inference Chip Is Competing with Nvidia?open.spotify.com

   ▲ 2sindamnataraj257ddiscusssavesaved
6. 06
   

   newAWS Marketplace: Cerebras Inference Cloudaws.amazon.com

   ▲ 1rbanffy452ddiscusssavesaved
7. 07
   

   newCerebras Launches Cerebras Inference Cloud Availability in AWS Marketplacewww.businesswire.com

   ▲ 1rbanffy452ddiscusssavesaved
8. 08
   

   newAMD and Cerebras Launch AI Inference Solutionwww.cerebras.ai

   ▲ 28rbanffy73d💬 9savesaved
9. 09
   

   newGemma 4 on Cerebras - The Fastest Inference Is Now Multimodalwww.cerebras.ai

   ▲ 24Tiberium97d💬 8savesaved
10. 10
    

    newCerebras brings instant inference to Mistral Le Chatcerebras.ai

    ▲ 3lis592ddiscusssavesaved
11. 11
    

    newThe state of "super fast inference" is frustrating

    ▲ 44k614d💬 1savesaved
12. 12
    

    newCerebras Inks Transformative $10B Inference Deal with OpenAIwww.nextplatform.com

    ▲ 3rbanffy259ddiscusssavesaved
13. 13
    

    newCerebras Brings Trillion Parameter Inference to Enterprises with Kimi K2.6www.cerebras.ai

    ▲ 2GaggiX138ddiscusssavesaved
14. 14
    

    newShow HN: RustyRAG lowest-latency open-source RAG on GitHubgithub.com

    ▲ 1zer0tokens215ddiscusssavesaved
15. 15
    

    newQwen 3.8 27B available on Cerebras at 1500 tokens/sinference-docs.cerebras.ai

    ▲ 691altertable32d💬 228savesaved
16. 16
    

    newImplementing Gist Memory: Summarizing, Searching Long Documents with a ReadAgentinference-docs.cerebras.ai

    ▲ 1rbanffy407ddiscusssavesaved
17. 17
    

    newImplementing Gist Memory: Summarizing and Searching Long Docs with a ReadAgentinference-docs.cerebras.ai

    ▲ 1rbanffy411ddiscusssavesaved
18. 18
    

    newMeta Collaborates with Cerebras in New Llama APIwww.cerebras.ai

    ▲ 1vrnvu524ddiscusssavesaved
19. 19
    

    newOpenAI Partners with Cerebraswww.cerebras.ai

    ▲ 2nezhar263d💬 3savesaved
20. 20
    

    newShow HN: OpenEvolve – open-source implementation of DeepMind's AlphaEvolve

    ▲ 8codelion503d💬 3savesaved
21. 21
    

    newCerebras now supports OpenAI GPT-OSS-120B at 3k Tokens Per SECwww.cerebras.ai

    ▲ 11me551ah426ddiscusssavesaved
22. 22
    

    newAsk HN: Why isn't everyone talking about (and using) Cerebras?

    ▲ 10ray__285ddiscusssavesaved
23. 23
    

    newCerebras Overclocks WSE-3 Waferscale Engine to Boost Inference in "Nexus" CS-4www.nextplatform.com

    ▲ 5rbanffy47ddiscusssavesaved
24. 24
    

    newDeepSeek R1 70B now available on Cerebras (1,500 tokens/s)cerebras.ai

    ▲ 4henry_viii613ddiscusssavesaved
25. 25
    

    newCerebras Announces Six New AI Datacenters Across North America and Europecerebras.ai

    ▲ 2ashvardanian572ddiscusssavesaved
26. 26
    

    newShow HN: Open-source turn detection model for voice AI

    ▲ 8russ651d💬 1savesaved
27. 27
    

    newShow HN: DeepThink Plugin – Bring Gemini 2.5's parallel reasoning to open models

    ▲ 4codelion474ddiscusssavesaved
28. 28
    

    newAsk HN: What are some good/fast coding models for Apple Silicon?

    ▲ 2LoganDark111d💬 2savesaved
29. 29
    

    newShow HN: Teamlibra/ry: a Zig framework for Cursor that makes prompting bettercodeberg.org

    ▲ 2keatonlivermore260d💬 1savesaved

· edit