Can RTX 5090 run Moondream 2?

Yes — runs locally

~216 tok/sec · Instant — feels like typing. No noticeable delay.

Your VRAM

32 GB

Model size

1.8B

Best quant

Q4_K_M

VRAM needed

1.5 GB

The verdict

The RTX 5090 (32 GB VRAM) handles Moondream 2 comfortably using the Q4_K_M quantization, which fits in 1.5 GB. Expected throughput is around 216 tokens/second, which feels Instant — feels like typing. No noticeable delay. in interactive use. Ultra-compact vision model. Only 1GB. Answers questions about images.

Setup tutorial: Moondream 2 on RTX 5090

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

TL;DR

Moondream 2 runs at Grade S on the NVIDIA GeForce RTX 5090 with Q4_K_M quantization, achieving ~1159 tok/sec.

Prerequisites

Before starting, ensure you have at least 2GB of free disk space, a compatible operating system (Windows or Linux), and the latest NVIDIA drivers (version 526.47 or later) installed along with CUDA 11.8.

Expected performance

With the recommended settings, Moondream 2 should achieve ~1159 tok/sec with 1.5GB VRAM in use, leaving 30.5GB of VRAM for context. This allows for a practical context window of up to 2048 tokens, making it suitable for complex multimodal tasks.

1. Install runtimeOllama

pip install ollama
ollama config set device cuda

2. Download the model

Download the Q4_K_M quantized version of Moondream 2 (1.0GB file) from Hugging Face.

ollama pull ggml-org/moondream2-20250414-GGUF:moondream2-20250414-Q4_K_M.gguf

3. Run it

ollama run moondream2-20250414-Q4_K_M.gguf --interactive
ollama chat --model moondream2-20250414-Q4_K_M.gguf

4. Optimize for RTX 5090

For optimal performance on the NVIDIA GeForce RTX 5090 with 32GB VRAM, use the --n-gpu-layers flag to offload layers to the GPU. Enable flash attention (--flash-attn) for faster inference. With 32GB VRAM, you can set --tensor-parallelism to 2 or 4 to further optimize throughput while maintaining a large context window.

Troubleshooting

Low token generation speed

Ensure that the --flash-attn flag is enabled and that the --n-gpu-layers is set appropriately for your GPU.

Out of memory errors

Reduce the value of --n-gpu-layers or decrease the context window size using the --context-length flag.

Model fails to load

Verify that the model file has been downloaded correctly and that the Ollama runtime is properly installed. Try reinstalling Ollama or pulling the model again.

Alternative runtimes

Alternative runtimes like LM Studio, llama.cpp, and Jan can be used for more advanced customization or specific use cases. LM Studio offers a graphical interface and is ideal for users who prefer a visual setup. llama.cpp provides low-level control and is suitable for developers who need fine-grained optimization. Jan is a lightweight option for quick prototyping and testing on the NVIDIA GeForce RTX 5090.

Full Moondream 2 details →

Other models that run great on RTX 5090

FAQ (20)

What GPU do I need to run Moondream 2?

To run Moondream 2, you need a GPU with at least 1.5 GB of VRAM. The model is optimized for low VRAM usage, making it suitable for older or budget GPUs.

Is Moondream 2 good for coding?

Moondream 2 is primarily designed for multimodal tasks, such as answering questions about images. It is not optimized for coding tasks, which typically require specialized language models.

Moondream 2 vs Llama 3.1 8B?

Moondream 2 has 1.8 billion parameters and is optimized for multimodal tasks, while Llama 3.1 8B is a larger language model with 8 billion parameters, better suited for text-only tasks. Moondream 2 requires less VRAM and is more compact.

Can I run Moondream 2 on a Mac?

Yes, Moondream 2 can be run on a Mac with a compatible GPU. Ensure your Mac has at least 1.5 GB of VRAM to handle the model efficiently.

How much VRAM does Moondream 2 need?

Moondream 2 requires 1.5 GB of VRAM, regardless of quantization. This makes it suitable for systems with limited GPU resources.

Is Moondream 2 censored?

Moondream 2 is not inherently censored. However, the model adheres to the Apache-2.0 license, which may include guidelines for responsible use.

Is Moondream 2 commercial-use allowed?

Yes, Moondream 2 is licensed under the Apache-2.0 license, which allows for commercial use without restrictions.

Moondream 2 context length?

Moondream 2 has a context length of 2048 tokens, allowing it to process longer sequences of text and image data.

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