canirunthismodel

Can I run gemma-2-9b-it on a NVIDIA H100 (80GB)?

Yes.Runs

You can run this comfortably. On a NVIDIA H100 (80GB) (80 GB VRAM), gemma-2-9b-it needs about 23 GB (FP16) and should generate at roughly ~100 tok/s. Recommended: Run on your GPU with FP16.

google/gemma-2-9b-it

Why

How to run gemma-2-9b-it on a H100 (80GB)

Serve with vLLM (OpenAI-compatible API)
# Fast production serving on http://localhost:8000/v1
vllm serve google/gemma-2-9b-it
Python (Transformers)
from transformers import pipeline
pipe = pipeline("text-generation", model="google/gemma-2-9b-it", device_map="auto")
print(pipe("Hello", max_new_tokens=50))

Want it to run comfortably at higher precision? The smallest GPU that runs gemma-2-9b-it well is the NVIDIA H200 (141 GB).

Try the full analyzer

gemma-2-9b-it on other GPUs

Other models on a H100 (80GB)