Can I run Mistral-7B-Instruct-v0.3 on a NVIDIA RTX 2080 Ti?
Yes.Runs
You can run this with Q8 quantization. On a NVIDIA RTX 2080 Ti (11 GB VRAM), Mistral-7B-Instruct-v0.3 needs about 9.7 GB (Q8) and should generate at roughly ~53 tok/s. Recommended: Run on your GPU with Q8.
mistralai/Mistral-7B-Instruct-v0.3Why
- Full precision needs ~18 GB which exceeds your accelerator, but 8-bit (INT8 / Q8) needs only ~9.7 GB and fits.
How to run Mistral-7B-Instruct-v0.3 on a RTX 2080 Ti
Run with Ollama (easiest)
ollama run mistral:7bOr with llama.cpp
llama-cli -hf mistralai/Mistral-7B-Instruct-v0.3 -p "Hello"Serve with vLLM (OpenAI-compatible API)
# Fast production serving on http://localhost:8000/v1
vllm serve mistralai/Mistral-7B-Instruct-v0.3Python (Transformers)
from transformers import pipeline, BitsAndBytesConfig
# pip install transformers accelerate bitsandbytes
quant = BitsAndBytesConfig(load_in_8bit=True)
pipe = pipeline("text-generation", model="mistralai/Mistral-7B-Instruct-v0.3", 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 Mistral-7B-Instruct-v0.3 well is the NVIDIA RTX 5070 (12 GB).