Can I run gemma-2-9b-it on a NVIDIA RTX 5080?
Yes.Runs
You can run this with Q8 quantization. On a NVIDIA RTX 5080 (16 GB VRAM), gemma-2-9b-it needs about 12 GB (Q8) and should generate at roughly ~63 tok/s. Recommended: Run on your GPU with Q8.
google/gemma-2-9b-itWhy
- Full precision needs ~23 GB which exceeds your accelerator, but 8-bit (INT8 / Q8) needs only ~12 GB and fits.
How to run gemma-2-9b-it on a RTX 5080
Run with Ollama (easiest)
ollama run gemma2:9bOr with llama.cpp
llama-cli -hf google/gemma-2-9b-it -p "Hello"Serve with vLLM (OpenAI-compatible API)
# Fast production serving on http://localhost:8000/v1
vllm serve google/gemma-2-9b-itPython (Transformers)
from transformers import pipeline, BitsAndBytesConfig
# pip install transformers accelerate bitsandbytes
quant = BitsAndBytesConfig(load_in_8bit=True)
pipe = pipeline("text-generation", model="google/gemma-2-9b-it", device_map="auto",
model_kwargs={"quantization_config": quant})
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 AMD RX 7900 XT (20 GB).