Cerebras Blog company blog
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.
- Points
- 427
- HN comments
- 156
- Submissions
- 1
- Cited by
- 0 commenters
AI & Machine LearningHardware & Electronics2024
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| Nov 19, 2024 | Llama 3.1 405B now runs at 969 tokens/s on Cerebras Inference by benchmarkist | 427 | 156 |
