Best local AI models for NVIDIA GT 755M

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 GT 755M is a mobile graphics card equipped with 2 GB of GDDR5 memory. This physical memory size is the absolute limit for running local AI models entirely on the hardware. To fit within this 2 GB boundary, models must use quantization. Quantization reduces the precision of model weights to save space. The quant column shows the best format that balances performance and size for each model.

For models up to 2.8B parameters, you can run them fully inside the graphics memory. The Allegro 2.8B model fits by using the Q4_K_M quant which consumes exactly 2 GB of memory. Similarly, Open-Sora Plan 2.7B uses the Q4_K_M quant to fit within 2 GB. The LFM2 2.6B and Playground v2.5 2.6B models both run on the Q4_K_M quant and require 1.9 GB of memory.

Slightly smaller models can use higher precision quants for better output quality. SmolVLM 2B, Stable Diffusion 3 Medium 2B, Pyramid Flow 2B, and Wav2Vec2 / XLS-R 2B all run at the Q6_K quant level using 2 GB of memory. For even smaller models like StableLM 2 1.6B, Sana 1.6B, Zonos 0.1 1.6B, and Dia 1.6B, you can use the high quality Q8_0 quant which utilizes 2 GB of memory.

When a model is too large for the 2 GB graphics memory, you must use CPU offload. This process splits the model weights between your graphics card and your system RAM. We assume your computer has 32 GB of system RAM for these setups. Offloading allows you to run larger models, but it costs speed because transferring data between system RAM and graphics memory is slow.

For example, SmolLM3 3B, Replit Code v1.5 3B, Kandinsky 3.1 3B, Voxtral Mini / Small 3B, Orpheus TTS 3B, and Higgs Audio v2 3B all need 2.2 GB of graphics memory at the Q4_K_M quant. They also require 4.2 GB of system RAM. MusicGen small/medium/large 3.3B needs 2.4 GB of graphics memory at Q4_K_M and 4.4 GB of system RAM.

Larger image generation models also rely on offloading. Stable Diffusion XL 3.417B needs 4.1 GB of memory at FP8 / optimized and 6.1 GB of system RAM. SDXL Turbo 3.5B and SDXL Lightning 3.5B both need 2.6 GB of graphics memory at Q4_K_M and 4.6 GB of system RAM. Be aware that running text models at a 4k context window increases memory usage and might require more offloading.