| | GPT-OSS 120B Runs at 3000 tokens/sec on Cerebras (cerebras.ai) |
| 47 points by samspenc 4 days ago | past | 29 comments |
|
| | Cerebras Code now supports GLM 4.6 at 1000 tokens/sec (cerebras.ai) |
| 192 points by nathabonfim59 4 days ago | past | 128 comments |
|
| | Moe 101 Guide: From Theory to Production (cerebras.ai) |
| 4 points by dmsobad 22 days ago | past | 2 comments |
|
| | Reap: One-Shot Pruning for Trillion-Parameter Mixture-of-Experts Models (cerebras.ai) |
| 3 points by todsacerdoti 25 days ago | past |
|
| | Cerebras systems raises $1.1B Series G (cerebras.ai) |
| 126 points by fcpguru 42 days ago | past | 75 comments |
|
| | Moe at Scale: Making Sparse Models Fast on Real Hardware (cerebras.ai) |
| 2 points by frozenseven 55 days ago | past |
|
| | Implementing Gist Memory: Summarizing, Searching Long Documents with a ReadAgent (cerebras.ai) |
| 1 point by rbanffy 79 days ago | past |
|
| | The Practitioner's Guide to the Maximal Update Parameterization (cerebras.ai) |
| 1 point by jxmorris12 82 days ago | past |
|
| | Implementing Gist Memory: Summarizing and Searching Long Docs with a ReadAgent (cerebras.ai) |
| 1 point by rbanffy 83 days ago | past |
|
| | How to build a router for MOE models (cerebras.ai) |
| 2 points by jxmorris12 3 months ago | past |
|
| | Cerebras now supports OpenAI GPT-OSS-120B at 3k Tokens Per SEC (cerebras.ai) |
| 11 points by me551ah 3 months ago | past |
|
| | Cerebras Code (cerebras.ai) |
| 449 points by d3vr 3 months ago | past | 172 comments |
|
| | Qwen3 Coder 480B is Live on Cerebras (cerebras.ai) |
| 47 points by retreatguru 3 months ago | past | 10 comments |
|
| | Qwen3 235B 2507 Instruct Now Available on Cerebras (cerebras.ai) |
| 5 points by mihau 3 months ago | past |
|
| | Cerebras launches Qwen3-235B, achieving 1.5k tokens per second (cerebras.ai) |
| 364 points by mihau 3 months ago | past | 155 comments |
|
| | Cerebras achieves 2,500T/s on Llama 4 Maverick (400B) (cerebras.ai) |
| 93 points by ByteAtATime 5 months ago | past | 93 comments |
|
| | Meta Collaborates with Cerebras in New Llama API (cerebras.ai) |
| 1 point by vrnvu 6 months ago | past |
|
| | Cerebras Announces Six New AI Datacenters Across North America and Europe (cerebras.ai) |
| 2 points by ashvardanian 8 months ago | past |
|
| | Cerebras brings instant inference to Mistral Le Chat (cerebras.ai) |
| 3 points by lis 8 months ago | past |
|
| | Mistral Flash Answers Run on Cerebras (cerebras.ai) |
| 5 points by jwan584 9 months ago | past | 1 comment |
|
| | DeepSeek R1 70B now available on Cerebras (1,500 tokens/s) (cerebras.ai) |
| 4 points by henry_viii 9 months ago | past |
|
| | 100x defect tolerance: How we solved the yield problem (cerebras.ai) |
| 331 points by jwan584 10 months ago | past | 179 comments |
|
| | Cerebras Demonstrates Trillion Parameter Model Training on a Single CS-3 System (cerebras.ai) |
| 1 point by rbanffy 11 months ago | past |
|
| | AIBI: Revolutionizing Interviews with AI (cerebras.ai) |
| 2 points by sandwichsphinx 11 months ago | past | 2 comments |
|
| | Llama 3.1 405B now runs at 969 tokens/s on Cerebras Inference (cerebras.ai) |
| 427 points by benchmarkist 11 months ago | past | 156 comments |
|
| | Cerebras Inference now 3x faster: Llama3.1-70B breaks 2,100 tokens/s (cerebras.ai) |
| 147 points by campers on Oct 25, 2024 | past | 84 comments |
|
| | Cerebras Inference now runs Llama 3.1-70B at 2100 tokens/s (cerebras.ai) |
| 6 points by cs-fan-101 on Oct 24, 2024 | past |
|
| | Simulating Human Behavior with Cerebras (cerebras.ai) |
| 2 points by akvadrako on Oct 17, 2024 | past |
|
| | Cerebras' third-generation wafer-scale engine (WSE-3) (cerebras.ai) |
| 2 points by doener on Aug 29, 2024 | past |
|
| | Llama 8B at 1800 tokens per second on Cerebras (cerebras.ai) |
| 2 points by huevosabio on Aug 28, 2024 | past |
|
|
| More |
