Best local AI models for Intel Arc A580

The largest models that fit fully

The 30 largest of the 123 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 A580 graphics card features 8 GB of GDDR6 memory. This dedicated video memory determines the maximum size of the artificial intelligence models you can run entirely on the hardware. To run a model smoothly without system slowdowns, the model files and the active context data must fit within this 8 GB limit.

The quantization column indicates the compression level applied to each model. Quantization reduces the precision of model weights to save space. For example, the Q4_K_M quant represents a four bit medium quantization, while Q5_K_M and Q6_K represent five bit and six bit formats. Higher quantization levels like Q6_K preserve more original model quality but require more memory.

Several high quality models fit directly into the 8 GB memory of the Intel Arc A580. You can run Mochi 1 10B at the Q4_K_M quantization level using 7.3 GB of memory. Gemma 2 9B fits at Q4_K_M using exactly 8 GB. Other 9B models like Nemotron Nano 4B / 9B, GLM-4 9B / GLM-4.5-Air, Yi-Coder 1.5B / 9B, GLM-4-9B-Chat / CodeGeeX4, and GLM-4V-9B / GLM-4.1V-Thinking fit at Q5_K_M using 7.7 GB. Chroma 8.9B fits at Q5_K_M using 7.6 GB, and Llama 3.1 8B fits at Q5_K_M using 7.4 GB.

Many 8B and 7B models run efficiently at the higher Q6_K quantization level. Granite 3.3 2B / 8B, Ministral 3B / 8B, InternLM 3 8B, OpenCoder 1.5B / 8B, Seed-Coder 8B, MiniCPM-V 2.6 / MiniCPM-o 2.6, Idefics 3 8B, Fuyu-8B, Emu3, and Stable Diffusion 3.5 Large / Turbo all use 7.9 GB at Q6_K. EXAONE 3.5 2.4B / 7.8B uses 7.7 GB at Q6_K. Mistral 7B uses 7.4 GB at Q6_K. Models like Qwen2.5 0.5B / 1.5B / 3B / 7B, OLMo 2 1B / 7B, Falcon 3 1B / 3B / 7B, Command R7B, OpenHermes 2.5, Zephyr 7B Beta, OpenChat 3.5, Starling LM 7B, and Codestral Mamba 7B all use 6.9 GB at Q6_K.

When a model exceeds the 8 GB video memory limit, you must offload parts of the model to your system RAM. This offloading process allows you to run larger models but reduces processing speed because system RAM is slower than GDDR6 memory. For offloading, we assume your computer has 32 GB of system RAM to handle the extra load.

With CPU offloading, you can run Open-Sora 2.0 11B at Q4_K_M, which needs 8.1 GB of video memory and 10.1 GB of system RAM. FLUX.1 dev 12B needs 14.4 GB at FP8 / optimized and 16.4 GB of system RAM. Gemma 3 12B, Gemma 4 12B, Mistral NeMo 12B, Pixtral 12B, FLUX.1 schnell 12B, FLUX.1 Kontext dev 12B, and FLUX.1 Krea dev 12B all need 8.8 GB at Q4_K_M and 10.8 GB of system RAM. Vicuna 13B needs 9.5 GB at Q4_K_M and 11.5 GB of system RAM.

Keep in mind that these memory calculations are based on a standard 4k context window. If you increase the context length to process longer documents or larger chat histories, the memory usage will rise. Running models close to the 8 GB limit with large context windows may cause the system to run out of memory or force slow offloading.