Best local AI models for NVIDIA MX330

The largest models that fit fully

The 30 largest of the 56 models that fit; every smaller model in the catalog fits too. Best quant means the highest quality compression whose weights and 4k context both sit inside the memory.

Close, but only with CPU offload

These need more than the card holds at their smallest practical quant, so part of the model runs from system memory (figures assume 32 GB of it). They work, several times slower.

How to read this

The NVIDIA MX330 is an entry level laptop graphics card equipped with 2 GB GDDR5 video memory. This dedicated memory size is the strict limit for running artificial intelligence models directly on your hardware. If a model exceeds this capacity, your computer must use system memory, which slows down performance. To run local models successfully on this card, you must select small architectures and use optimized quantization formats.

Quantization is a compression method that reduces the size of a model. The quant column shows the best balance of quality and memory usage for each model on this hardware. For example, a Q4_K_M quant uses four bit quantization to fit larger models like Allegro 2.8B or Open-Sora Plan 2.7B into your 2 GB limit. Higher quants like Q8_0 provide better accuracy but require smaller models like TinyLlama 1.1B to avoid running out of video memory.

You can run models that exceed your video memory by using CPU offload. This technique splits the workload between your graphics card and your system RAM. If you have 32 GB of system RAM, you can run larger models like SmolLM3 3B or Kandinsky 3.1. These models require 2.2 GB of video memory at Q4_K_M and an additional 4.2 GB of system RAM to function.

CPU offload also enables image generation models on your system. Stable Diffusion XL requires 4.1 GB at FP8 or optimized settings, which uses 6.1 GB of system RAM. Similarly, SDXL Turbo and SDXL Lightning require 2.6 GB of video memory at Q4_K_M and 4.6 GB of system RAM. While offloading allows these models to run, the transfer of data between your graphics card and system RAM will result in slower generation speeds.

When running text models, you must consider the context window size. The memory figures listed are calculated using a standard 4k context window. If you increase the context window to process longer documents, the memory usage will rise quickly. To prevent system crashes on your 2 GB card, you should keep your context window at 4k or lower.