Best local AI models for Intel Arc A730M

The largest models that fit fully

The 30 largest of the 147 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 Intel Arc A730M laptop graphics card features 12 GB of GDDR6 video memory. This dedicated memory size determines which artificial intelligence models you can run entirely on your hardware. To run a model smoothly, the model files and the active conversation data must fit within this 12 GB limit. If a model exceeds this capacity, your system will slow down significantly.

Quantization is a method that compresses model files to save space. The quant column shows the best compression level for each model on this hardware. For example, DeepSeek-Coder-V2 16B and Kimi-VL A3B both use the Q4_K_M quant to fit into 11.7 GB of memory. Models like Gemma 3 12B and Mistral NeMo 12B can use the higher quality Q6_K quant which uses 11.8 GB of memory. Smaller models like GLM-4 9B can run at the Q8_0 quant using 11.4 GB of memory.

When a model is slightly too large for the 12 GB video memory, you can use CPU offloading. This process shares the workload between your graphics card and your system memory. We assume your system has 32 GB of system RAM for these calculations. For example, running FLUX.1 dev at FP8 requires 14.4 GB of memory, which uses 16.4 GB of system RAM. Codestral 22B requires 16.1 GB at the Q4_K_M quant, which uses 18.1 GB of system RAM.

CPU offloading allows you to run larger models like CogVLM2 or Solar Pro, but it comes with a performance cost. Moving data between the system RAM and the graphics card is much slower than keeping everything inside the GDDR6 memory. Your generation speed will drop when offloading is active. For the fastest generation speeds, you should select models that fit completely within the 12 GB video memory limit.

Memory calculations must also account for the context window. The memory figures listed here are calculated with a standard 4k context window. If you input very long documents or have long conversations, the memory usage will increase. A larger context window might push a model that normally fits inside the 12 GB limit into system RAM offloading.