top | item 41369110 cerebras: 450 tokens/sec llama 3.1 70B 7 points| davidfiala | 1 year ago |theregister.com 2 comments order hn newest IronWolve|1 year ago Cerebras fails the "how many r's in strawberry" test. Grok is the only one who passed that test.Going to be interesting to see the speed and accuracy keep increasing, cant imagine how fast/accurate things will be in a decade. Cant wait. davidfiala|1 year ago - 1,800tps on llama 3.1 8B- 450tps on llama 3.1 70Bfree chat interface is at: https://inference.cerebras.ai (requires login)
IronWolve|1 year ago Cerebras fails the "how many r's in strawberry" test. Grok is the only one who passed that test.Going to be interesting to see the speed and accuracy keep increasing, cant imagine how fast/accurate things will be in a decade. Cant wait.
davidfiala|1 year ago - 1,800tps on llama 3.1 8B- 450tps on llama 3.1 70Bfree chat interface is at: https://inference.cerebras.ai (requires login)
IronWolve|1 year ago
Going to be interesting to see the speed and accuracy keep increasing, cant imagine how fast/accurate things will be in a decade. Cant wait.
davidfiala|1 year ago
- 450tps on llama 3.1 70B
free chat interface is at: https://inference.cerebras.ai (requires login)