Meta Llama 3 1 8b Instruct Bnb 4bit

No PawBench serving benchmark yet

This model hasn't been benchmarked with PawBench on any hardware. Be the first to contribute!

How to contribute

  1. 1. pip install servingcard
  2. 2. servingcard benchmark --model meta-llama-3-1-8b-instruct-bnb-4bit --hardware your-gpu
  3. 3. Submit a PR to the registry

Discussion

Know something about serving this model? Share your experience.