1
Accelerating GPT-5.6 Sol Ultrafast
See how Cerebras powers GPT-5.6 Sol in OpenAI's Ultrafast mode at up to 750 output tokens per second for time-sensitive AI and agent workflows.
Cerebras Blog
Cerebras powers the world's fastest AI inference on the biggest wafer chip. Cerebras CS-4 delivers up to 30x faster inference than GPUs.
- Popular posts
- 9
- Total points
- 3,099
- HN comments
- 1,314
- Rank
- #381 company
Visit cerebras.ai → On Hacker News Aug 2024 – Oct 2026
AI & Machine Learning 9Hardware & Electronics 5Tech Industry & Business 2Software Engineering 1Infrastructure & DevOps 1
2
Llama 3.1 405B now runs at 969 tokens/s on Cerebras Inference
Llama 3.1 405B on Cerebras is by far the fastest frontier model in the world – 12x faster than GPT-4o and 18x faster than Claude 3.5 Sonnet.
3
100x defect tolerance: How we solved the yield problem
Cerebras powers the world's fastest AI inference on the biggest wafer chip. Cerebras CS-4 delivers up to 30x faster inference than GPUs.
4
Cerebras Inference: AI at Instant Speed
We are excited to announce the release of Cerebras DocChat, our first iteration of models designed for document-based conversational question answering. This series includes two models: Cerebras Llama3-DocChat, a large language model (LLM), and Cerebras Dragon-DocChat, a multi-turn retriever model.
5
Cerebras Inference now 3x faster: Llama3.1-70B breaks 2,100 tokens/s
Cerebras powers the world's fastest AI inference on the biggest wafer chip. Cerebras CS-4 delivers up to 30x faster inference than GPUs.