Can I run Qwen2.5-32B-Instruct on a NVIDIA RTX 3090?
Yes.Runs
You can run this with Q3 quantization. On a NVIDIA RTX 3090 (24 GB VRAM), Qwen2.5-32B-Instruct needs about 18 GB (Q3) and should generate at roughly ~43 tok/s. Recommended: Run on your GPU with Q3.
Qwen/Qwen2.5-32B-InstructWhy
- Full precision needs ~80 GB which exceeds your accelerator, but 3-bit (Q3_K) needs only ~18 GB and fits.
How to run Qwen2.5-32B-Instruct on a RTX 3090
Run with Ollama (easiest)
ollama run qwen2.5:32bOr with llama.cpp
llama-cli -hf Qwen/Qwen2.5-32B-Instruct -p "Hello"Serve with vLLM (OpenAI-compatible API)
# Fast production serving on http://localhost:8000/v1
vllm serve Qwen/Qwen2.5-32B-InstructPython (Transformers)
from transformers import pipeline, BitsAndBytesConfig
# pip install transformers accelerate bitsandbytes
quant = BitsAndBytesConfig(load_in_4bit=True)
pipe = pipeline("text-generation", model="Qwen/Qwen2.5-32B-Instruct", 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 Qwen2.5-32B-Instruct well is the NVIDIA RTX 5090 (32 GB).