Best local AI models for NVIDIA MX550

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 MX550 is an entry level laptop graphics card equipped with 2 GB of GDDR6 memory. This dedicated memory size is the strict limit for running artificial intelligence models directly on your hardware. If a model exceeds this capacity it cannot run entirely on the graphics card. To get the best speed you must select models that fit within this 2 GB boundary.

The quantization column shows the optimal format for each model. Quantization compresses the weights of a model to reduce its memory footprint. For example the 2.8B Allegro model fits in 2 GB of memory when using the Q4_K_M quantization. Other models like the 2B Stable Diffusion 3 Medium can run with the higher quality Q6_K quantization while still staying within the 2 GB limit.

Models like the 1.6B StableLM 2 or the 1.55B Whisper Large v3 use the Q8_0 quantization which consumes exactly 2 GB of memory. Smaller models such as the 1.1B TinyLlama require only 1.4 GB of memory at Q8_0. Choosing the correct quantization is essential to balance output quality and memory usage on this hardware.

When a model is too large for the 2 GB graphics memory you can use CPU offload if your computer has 32 GB of system RAM. This process splits the workload between your graphics card and your system memory. For example the 3B SmolLM3 requires 2.2 GB of graphics memory at Q4_K_M and an additional 4.2 GB of system RAM. This offload method allows you to run larger models but it reduces processing speed.

Other offload examples include the 3.5B SDXL Turbo which needs 2.6 GB of graphics memory at Q4_K_M and 4.6 GB of system RAM. The 3.417B Stable Diffusion XL requires 4.1 GB of graphics memory at FP8 and 6.1 GB of system RAM. While offloading enables these larger tools it introduces a performance cost because system RAM is much slower than GDDR6 memory.

You must also consider the memory cost of context length. Running a model with a standard 4k context window requires additional memory for the active conversation history. This extra memory usage is not included in the base model size. If you use the maximum context length you may need to select a smaller model like the 1.7B Qwen3 to prevent running out of memory.