Best local AI models for AMD E8860

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 E8860 is an embedded graphics card equipped with 2 GB of GDDR5 memory. This dedicated memory size determines which artificial intelligence models can run directly on the hardware. To run a model entirely on this GPU, the model files and active memory must fit within this 2 GB limit. If a model exceeds this capacity, it cannot run on the graphics card alone.

The quantization column shows the compression level used to fit these models into the hardware. Quantization reduces the precision of model weights to save space. For example, the Allegro 2.8B model fits into 2 GB of memory when using the Q4_K_M quantization. Smaller models like SmolLM2 1.7B can use the higher quality Q6_K quantization while staying within 1.7 GB of memory. Models like TinyLlama 1.1B can run at the Q8_0 quantization level using 1.4 GB of memory.

When a model is slightly too large for the 2 GB graphics memory, you can use CPU offload. This technique splits the model between your graphics card and your system RAM. We assume your system has 32 GB of system RAM for these calculations. Offloading allows you to run larger models, but it reduces processing speed because data must travel between the CPU and GPU.

For instance, the SmolLM3 3B model needs 2.2 GB of memory at the Q4_K_M quantization. By offloading, it uses your 2 GB of graphics memory and requires 4.2 GB of system RAM. Similarly, the Stable Diffusion XL model requires 4.1 GB of memory at FP8 or optimized settings, which requires 6.1 GB of system RAM to run via offload. Other models like SDXL Turbo and SDXL Lightning need 2.6 GB at Q4_K_M, which translates to 4.6 GB of system RAM.

You must also consider the context window size when running these models. The memory numbers listed here are calculated for a standard 4k context window. If you increase the context window to process longer text or more data, the memory usage will rise. This extra memory demand can push a fitting model over the 2 GB limit and force you to use CPU offload.