Re:Thefastest.ai
by saltsaman on Tuesday April 23, 2024 @05:53PM
(#40137788)
Couple of things:
1. Filtering by model should be enabled by default. Mixtral-8x7b-instruct on Perplexity is almost as fast as the 7B Llama 2 on fireworks, but are quite different in sizes.
2. Pricing is a very important factor that is not included.
3. Overall service reliability should also be an important signal.
Re:Thefastest.ai
by juberti on Tuesday April 23, 2024 @05:57PM
(#40137834)
Can you describe what you'd like to see for #1? We currently show everything, but let people filter via the UI or URL param, e.g., https://thefastest.ai/?mf=3-70
1. Filtering by model should be enabled by default. Mixtral-8x7b-instruct on Perplexity is almost as fast as the 7B Llama 2 on fireworks, but are quite different in sizes.
2. Pricing is a very important factor that is not included.
3. Overall service reliability should also be an important signal.