Best local AI models for AMD HD 8730M

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 AMD Radeon HD 8730M is a mobile graphics processor equipped with 2 GB of DDR3 video memory. This memory capacity dictates the size of the artificial intelligence models you can run locally. To load a model entirely onto this hardware, the model files and the active workspace must fit within the 2 GB limit. Running models locally ensures your data remains private and does not rely on an internet connection.

To fit models onto this hardware, developers use quantization. Quantization reduces the precision of model weights to shrink the file size. The quant column indicates the best format for each model. For example, the Allegro 2.8B model fits within 2 GB of video memory when using the Q4_K_M quantization. Smaller models like Moondream 2 at 1.9B can use the higher quality Q6_K quantization while staying under the 1.9 GB threshold. TinyLlama 1.1B can run at Q8_0 quantization using 1.4 GB of video memory.

When a model exceeds the 2 GB limit, you must use CPU offload. This technique splits the model between your graphics card and your system memory. We assume your computer has 32 GB of system RAM for these scenarios. For instance, running the SmolLM3 3B model requires 2.2 GB of video memory at Q4_K_M quantization and an additional 4.2 GB of system RAM. Offloading allows you to run larger models like Stable Diffusion XL, which needs 4.1 GB of video memory at FP8 and 6.1 GB of system RAM.

Using CPU offload comes with a performance cost. System RAM is much slower than video memory. When parts of the model run on your system processor and RAM, generation speeds drop significantly. While offloading allows you to run the 3.5B SDXL Turbo model by using 2.6 GB of video memory and 4.6 GB of system RAM, the generation process will take longer than running a fully contained model.

You must also consider the context window when running text models. The memory figures listed are calculated for a standard 4k context window. If you increase the context length to process longer documents or extended conversations, the memory requirements will rise. This extra memory demand might push a model like the Qwen3 1.7B past its 1.7 GB limit, requiring you to use CPU offload or switch to a smaller model.