How to run a local LLM on the Intel Arc B580
A step-by-step setup for beginners. With 12 GB of graphics memory, the best everyday model for this card is Gemma 4 12B, which runs fast: a paragraph in a couple of seconds.
What to run on the Intel Arc B580
The best model for each job that fits fully in memory at the default Q4_K_M download and runs at a comfortable reading speed.
| Job | Model | Speed | Ollama command |
|---|---|---|---|
| Chat and everyday questions |  Gemma 4 12B | Fast: a paragraph in a couple of seconds | ollama run gemma4:12b |
| Help with code |  Qwen2.5 Coder 14B | Fast: a paragraph in a couple of seconds | ollama run qwen2.5-coder:14b |
| Writing and editing | Gemma 3 12B | Fast: a paragraph in a couple of seconds | ollama run gemma3:12b |
| Questions about my documents | Gemma 3 12B | Fast: a paragraph in a couple of seconds | ollama run gemma3:12b |
| Maths, logic and homework |  Phi-4 Reasoning 14B | Fast: a paragraph in a couple of seconds | ollama run phi4-reasoning:14b |
Set up Gemma 4 12B in about ten minutes
On Intel Arc cards LM Studio is the easier choice: it uses Vulkan, which works with most Arc cards. Pick one app. LM Studio is easiest if you've never used a terminal.
LM Studio on Windows
- Go to lmstudio.ai and click Download for Windows.
- Open the downloaded installer and click through it. LM Studio opens when it finishes.
- If it offers to download a first model, you can skip that. Click the search (magnifying glass) icon in the left sidebar to open Discover.
- Type Gemma 4 12B in the search box and pick the result from a well-known publisher such as lmstudio-community.
- Choose the Q4_K_M download if a list of versions appears. LM Studio marks versions that fit your GPU with a green "Full GPU offload possible" label. Click Download and wait for it to finish.
- Open the Chat tab, click Select a model to load at the top, pick Gemma 4 12B, and type your first message.
Ollama on Windows
- Go to ollama.com/download and download the Windows installer.
- Run OllamaSetup.exe. When it finishes, Ollama keeps running in the background (look for the llama icon by the clock).
- Open PowerShell (search for "PowerShell" in the Start menu) and run the command below. The first time, it downloads Gemma 4 12B, which can take a while.
ollama run gemma4:12b- When you see
>>>, type a message and press Enter. Type/byeto quit. Ollama's own app window can also chat with any model you have downloaded.
On Linux? Follow the LM Studio or Ollama Linux guide instead.
If something goes wrong
The four problems beginners hit most.
Out of memory or won't load
The model plus its working memory doesn't fit in your graphics memory. Here is how to make it fit, from the easiest fix to the most advanced.
It's really slow
Most slowness comes from the model not fitting fully in graphics memory, or from "thinking" models reasoning before they answer.
It's not using my GPU
If your graphics card sits idle while the CPU does all the work, one of these is usually the reason.
Weird, wrong or repeating answers
Local models can be excellent, but small or badly configured ones make mistakes that paid assistants don't. Here is what to check.
Run it in the cloud
Want a bigger model than the Intel Arc B580 can hold?
Rent a GPU with more memory by the hour, or see whether upgrading or renting is cheaper for you.
Frequently asked questions
What is the best local LLM for the Intel Arc B580?
For everyday chat, Gemma 4 12B: it fits in the Intel Arc B580's 12 GB at Q4_K_M and runs at about 38 tokens per second.
Should I use LM Studio or Ollama on the Intel Arc B580?
LM Studio is the easier choice on Intel Arc cards because it uses Vulkan, which works out of the box. Ollama support for Arc is newer and needs more setup.
Can the Intel Arc B580 run a 70B model?
Not fully in memory: a 70B model needs about 46.1 GB at Q4_K_M. It would spill into system RAM and run very slowly, so renting a GPU is the practical option.