Can RTX 3090 Ti run Llama 3.1 70B Instruct?

Yes — runs locally

~0 tok/sec · Cannot run — insufficient VRAM

Your VRAM

24 GB

Model size

70B

Best quant

Q4_K_M

VRAM needed

40.1 GB

The verdict

The RTX 3090 Ti (24 GB VRAM) handles Llama 3.1 70B Instruct comfortably using the Q4_K_M quantization, which fits in 40.1 GB. Expected throughput is around 0 tokens/second, which feels Cannot run — insufficient VRAM in interactive use. Meta's flagship 70B parameter model. Excellent performance rivaling GPT-4 on many benchmarks.

Setup tutorial: Llama 3.1 70B Instruct on RTX 3090 Ti

AI-generated, GPU-specific. Verified commands for your exact hardware.

TL;DR

Llama 3.1 70B Instruct runs on an NVIDIA GeForce RTX 3090 Ti with a grade D, using the Q4_K_M quantization, achieving ~13 tok/sec.

Prerequisites

Before starting, ensure you have at least 40GB of free disk space, a 64-bit version of Windows or Linux, NVIDIA driver version 470 or later, and CUDA 11.4 or later installed.

Expected performance

You can expect the model to run at ~13 tok/sec with 40.1GB VRAM in use, leaving -16.1GB of VRAM for context. This means the practical context window will be limited due to the available VRAM, but the model should still be usable for many tasks.

1. Install runtimeOllama

pip install ollama
ollama config set device cuda

2. Download the model

Download the Q4_K_M quantized model (39.6GB) from Hugging Face.

ollama pull bartowski/Meta-Llama-3.1-70B-Instruct-GGUF:Meta-Llama-3.1-70B-Instruct-Q4_K_M.gguf

3. Run it

ollama run Meta-Llama-3.1-70B-Instruct-Q4_K_M --n-gpu-layers 24 --flash-attn
ollama chat Meta-Llama-3.1-70B-Instruct-Q4_K_M

4. Optimize for RTX 3090 Ti

For optimal performance on the NVIDIA GeForce RTX 3090 Ti with 24GB VRAM, use --n-gpu-layers 24 to load as many layers as possible onto the GPU. Enable flash attention with --flash-attn to reduce memory usage and improve speed. Given the 40.1GB VRAM requirement, you will have approximately -16.1GB of VRAM left for context, which limits the practical context window.

Troubleshooting

Out of memory error during inference

Reduce the number of GPU layers with --n-gpu-layers 16 or lower, or decrease the context length with --context-length 65536.

Slow inference speed

Ensure flash attention is enabled with --flash-attn and try increasing the batch size with --batch-size 16.

Model fails to load

Verify the model file integrity and try re-downloading it. Ensure your CUDA installation is correct and up-to-date.

Alternative runtimes

Alternative runtimes like LM Studio, llama.cpp, and Jan can be used for more fine-grained control over performance and resource usage. LM Studio is suitable for users who prefer a GUI, while llama.cpp offers more flexibility in quantization options. Jan is ideal for those who need a lightweight, portable solution.

Full Llama 3.1 70B Instruct details →

Other models that run great on RTX 3090 Ti

FAQ (20)

What GPU do I need to run Llama 3.1 70B Instruct?

To run Llama 3.1 70B Instruct, you need a GPU with at least 40.1 GB of VRAM. Higher VRAM (up to 142.0 GB) is required for full precision or lower quantization levels.

Is Llama 3.1 70B Instruct good for coding?

Yes, Llama 3.1 70B Instruct performs well in coding tasks, often rivaling GPT-4 in code generation and understanding complex programming concepts.

Llama 3.1 70B Instruct vs Llama 3.1 8B?

Llama 3.1 70B Instruct offers significantly better performance and more nuanced responses compared to Llama 3.1 8B, but requires much more VRAM and computational resources.

Can I run Llama 3.1 70B Instruct on a Mac?

Yes, you can run Llama 3.1 70B Instruct on a Mac with a compatible GPU, such as an AMD Radeon Pro or NVIDIA GPU, provided it meets the VRAM requirements.

How much VRAM does Llama 3.1 70B Instruct need?

Llama 3.1 70B Instruct requires between 40.1 GB and 142.0 GB of VRAM, depending on the quantization level used.

Is Llama 3.1 70B Instruct censored?

Llama 3.1 70B Instruct is not inherently censored, but it may have content filters in place to prevent harmful or inappropriate content generation.

Is Llama 3.1 70B Instruct commercial-use allowed?

Yes, Llama 3.1 70B Instruct can be used commercially under the terms of its license, which allows for both research and commercial applications.

Llama 3.1 70B Instruct context length?

Llama 3.1 70B Instruct has a context length of 131,072 tokens, allowing it to process very long sequences of text.

Want personalized recommendations for your exact setup? Detect my hardware →