Best local AI models for Intel Arc B580

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 B580 graphics card features 12 GB of GDDR6 dedicated memory. This memory pool determines the maximum size of the artificial intelligence models you can run entirely on your local hardware. When a model fits completely inside this video memory, it runs at maximum speed because the graphics processor can access the parameters instantly.

The quantization column indicates the compression level used to shrink each model. Quantization reduces the precision of the model weights to save space. For example, the DeepSeek-Coder-V2 16B model fits within 11.7 GB of memory when using the Q4_K_M quantization. Other models like Gemma 3 12B and Mistral NeMo 12B can run at a higher quality Q6_K quantization while using 11.8 GB of memory.

Models like Phi-4 and Wan 2.2 T2I use 11.9 GB of memory at the Q5_K_M quantization level. If you select a model with a lower parameter count, you can use even less compression. The Nemotron Nano 9B and GLM-4 9B models run at the high quality Q8_0 quantization level, which requires 11.4 GB of memory.

When a model is too large for the 12 GB memory limit, you must use CPU offload. This process splits the model between your graphics card and your system memory. For example, running the FLUX.1 dev 12B model at FP8 requires 14.4 GB of memory, which uses 16.4 GB of system RAM. Running Codestral 22B requires 16.1 GB of memory at Q4_K_M, which uses 18.1 GB of system RAM. CPU offload allows you to run these larger models but slows down the generation speed significantly.

You must also account for the context window when calculating memory usage. The memory figures listed here assume a standard 4k context window. If you increase the context window to process longer documents or chat histories, the system will require more memory. This extra memory demand can push a model past the 12 GB limit and force the system into slow CPU offload mode.