GPT-OSS 120B Runs at 3000 tokens/sec on Cerebras(cerebras.ai)

20 points by samspenc 11 months ago | 12 comments

Cerebras Code(cerebras.ai)

423 points by d3vr 1 year ago | 165 comments

Cerebras blog post announcing Cerebras Code Pro ($50/month) and Code Max ($200/month) plans offering fast Qwen3-Coder inference at up to 2,000 tokens per second.

Accelerating GPT-5.6 Sol Ultrafast(cerebras.ai)

678 points by pr337h4m 2 months ago | 263 comments

Cerebras blog post announcing that it powers OpenAI's Ultrafast Mode for GPT-5.6 Sol in the OpenAI API, delivering up to 750 output tokens per second.

Cerebras Launches the Fastest AI Inference(cerebras.ai)

57 points by srameshc 2 years ago | 2 comments

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

75 points by ByteAtATime 1 year ago | 49 comments

Quasar 438B: Europe's Leading AI Model(multiversecomputing.com)

183 points by amunozo 1 month ago | 118 comments

Cerebras CS-4(cerebras.ai)

441 points by sunils34 2 months ago | 256 comments

Cerebras product page introducing the CS-4, which the company bills as the fastest AI accelerator in the industry.

Cerebras Deploys Trillion-Parameter AI Models(cerebras.ai)

349 points by gmays 1 day ago | 127 comments

Cerebras blog post explaining how trillion-parameter models like Kimi K3 are split across multiple WSE-3T wafers for pipelined, high-throughput inference.

Google to invest up to $2B in Anthropic(reuters.com)

356 points by fofoz 3 years ago | 338 comments

Reuters news article reporting that Google agreed to invest up to $2 billion in OpenAI rival Anthropic, published October 27, 2023.

OpenAI closes funding round at an $852B valuation(cnbc.com)

493 points by surprisetalk 6 months ago | 457 comments

OpenAI announcement that it closed a $122 billion funding round at an $852 billion post-money valuation.

OpenRouter raises $113M Series B(openrouter.ai)

431 points by freeCandy 4 months ago | 206 comments

OpenRouter's announcement of a $113M Series B round led by investors including CapitalG, Andreessen Horowitz, and Menlo Ventures.

Performance per dollar is getting faster and cheaper(wafer.ai)

345 points by latchkey 3 months ago | 133 comments

Wafer blog post on serving the GLM-5.2 model on AMD MI355X GPUs at 2626 tok/s per node and 213 tok/s single stream, at over 2x lower cost than Nvidia Blackwell.