canirunthismodel

Can I run Llama-3.1-8B-Instruct on a NVIDIA RTX 4090?

Yes.Runs

You can run this comfortably. On a NVIDIA RTX 4090 (24 GB VRAM), Llama-3.1-8B-Instruct needs about 20 GB (FP16) and should generate at roughly ~40 tok/s. Recommended: Run on your GPU with FP16.

meta-llama/Llama-3.1-8B-Instruct

Why

How to run Llama-3.1-8B-Instruct on a RTX 4090

Serve with vLLM (OpenAI-compatible API)
# Fast production serving on http://localhost:8000/v1
vllm serve meta-llama/Llama-3.1-8B-Instruct
Python (Transformers)
from transformers import pipeline
pipe = pipeline("text-generation", model="meta-llama/Llama-3.1-8B-Instruct", device_map="auto")
print(pipe("Hello", max_new_tokens=50))

Want it to run comfortably at higher precision? The smallest GPU that runs Llama-3.1-8B-Instruct well is the NVIDIA RTX 5090 (32 GB).

Try the full analyzer

Llama-3.1-8B-Instruct on other GPUs

Other models on a RTX 4090