JustOverride

Here is the information I found, I've checked it for accuracy. Sources included. At the end of the day, you always want firmware up-to-date. The bundled firmware update inside the Intel Arc Windows driver installer primarily delivers low-level Video BIOS (vBIOS) and Graphics Security Control (GSC) microcode updates directly to the hardware. Intel integrated this behavior to ensure cards function correctly without relying on separate flashing tools or Windows Update. [1, 2, 3, 4] Because these updates are embedded directly within the standard driver packages, they do not usually have standalone release notes, but they provide the foundational mechanics for several critical GPU behaviors. [1, 2] What is Included and Managed by the Firmware Update HDMI & DisplayPort Compatibility: Updates core display handshaking protocols to resolve "no signal" issues and blank screens when waking a computer from sleep or during a cold boot. [1] System Stability Fixes: Adjusts low-level power states to fix hard system hangs, sleep-to-wake crashes, and erratic power-cycling bugs inherent to the physical board. [1, 2] Fan Curves & Thermal Management: Recalibrates fan controller behavior on reference models to optimize thermal throttling limits and reduce fan-speed oscillation. Resizable BAR (ReBAR) Optimization: Tweaks how the GPU maps its VRAM memory allocation to the CPU, which is vital for the card's overall stability and frame-rate delivery. Security & Virtualization Adjustments: Modifies the integrated Graphics Security Control (GSC) processor. On enterprise variant cards (like the Arc Pro series), firmware changes are used to regulate and limit SR-IOV Virtual Functions. [1, 2, 3] Important Installation Notes It Installs Automatically: The Intel Arc driver installer will flash the firmware automatically if it detects your card is running an older vBIOS version. Longer Install Times: When a firmware bundle is being applied, the installer will take significantly longer to complete. Your screen may flicker or remain black longer than a normal driver update. Do Not Interrupt: It is critical that you do not power down, restart, or unplug your PC while this installer is running to avoid corrupting the GPU's onboard flash memory. [1]

I thought of this but the best way to keep the most resources is to not have to split the card and not have to run a VM. This works pretty well and will hold me up until better support becomes available. ONE NOTE: I forgot to add, this (and maybe other ARC cards as well) need to be connected to a baremetal PC running windows first! The Intel Drivers installer also contains a firmware update for the card, and this is the only delivery method. I would not suggest doing this through a pass-through VM.

I made a new post to get AI working well on these cards. https://forums.unraid.net/topic/199450-intel-arc-battlemage-b570-b580-b50-b70-etc-ai-support-in-unraid/

I've finally got AI working on my B70. I had searched a lot online and nothing was coming up due to software support not being available. Here is what I found was working, and what you'll need. - The graphics card NEEDS to be connected to a baremetal PC running windows first! The Intel driver installer contains a firmware update for the card, and this is the only delivery method. I would not suggest doing this through a pass-through VM. - Bios up-to-date, Resizable BAR (ReBAR) enabled, 'Above 4G' enabled. - Running Unraid 7.3.1. or above. - Have the plugin 'Intel GPU TOP' installed. I have tried multiple AI docker containers, and found that only llama.cpp works best, others don't work, or have very very little functionality. Check previous findings here if you're interested. Here are me settings for this docker container. Notes: - The model location has to be inside of your selected models folder defined in "Model Storage Path". For the post argument, you only need to add the file name. - My setup has an intel 14700K which has integrated iGPU, it is possible you may need to change the Post Argument last part to --device SYCL1 (or maybe remove that part), if you have more cards or a different setup. Con to this setup, when you have to change the model you have to do it in the post argument, it can't be done from the UI or from open-webUI. My open-webUI connection looks like this:

I love this machine, great components, nice setup, beautiful. Definitely a great turn key solution for small-medium businesses, and anyone who just want everything done. (turns on firewall) However; most people here know how to build-setup their own server, so building this machine (different similar case) with some drives would come-in at about 1K $ less, here in the U.S. anyway.

Updated successfully from Version: 7.3.0-rc2 to Version: 7.3.1 without issues!

Hopefully we should have better support soon. Also Ed (spaceinvader) said in his latest video (in the comments) that he would include a setup for intel cards in his upcoming video. He created one of the docker containers that support Intel Arc, so I’m hopeful.

I agree, that's exactly what I found. I've basically have a very expensive transcoding card, and can only use old models. But I'll be patient, I'll happily put my money where it hurts these other greedy companies.

Uptime 2 days 17 hours 40 minutes, no issues at all. Everything working as it should.

My Intel Arc B70 is working, your B50 should as well.

Current Version: Unraid 7.3.0-rc.1 ->> New Version: Unraid 7.3.0-rc.2 Everything looks fine!

So I got the Intel Arc Pro B70 because I didn't wanted to support NVIDIA, AMD, or OpenAI. I want to support affordable local AI options, and privacy. However, I have only been able to use Intel-IPEX-LLM-Ollama (uberchuckie/ollama-intel-gpu:latest) with Open-WebUI to support a very limited amount of models. Qwen 3.6 - Gives me an error (unable to load model: /root/.ollama/models/blobs/sha256-f5ee307a29.....) Gemma4 - Won't even download (pull model manifest: 412: The model you are attempting to pull requires a newer version of Ollama. Please download the latest version at: https://ollama.com/download) Note: Ollama is already fully up-to-date. Ministral-3 - Won't download either (pull model manifest: 412: The model you are attempting to pull requires a newer version of Ollama. Please download the latest version at: https://ollama.com/download) nemotron-3-nano:30b - Won't download... So I'm just wondering if I'm just stuck with llama3.1 and Deepseek-r1, and waiting for further development or how can I actually use the card now ?

B70 owner, I see 4 VF's, haven't tried it yet though as I mainly got this for AI.

I'm not too experience in setting up AI, specially on unraid, but this is literally turning into a headache. If I don't figure this out soon I'll be returning the card because I didn't buy this to host 25~ concurrent 4K streams on Plex.

This B70 replaced my Intel Arc 310 ECO, so that I can do all my homelab things and have AI. Note, it wasn't fully showing up for me on Version: 7.2.3, I had to upgrade to 7.3rc1. Also, you must 'accept the changes under 'tools -> devices'. Status with Arc B70: Plex (Working) Jellyfin (Working) Immich (Working) Ollama (Working) (most new models Qwen, Gemma4 aren't working, might need to switch to something else) Commands to keep handy for the unraid terminal Check the detected cards: ls /dev/dri lspci -nnk | grep -A 3 VGA Check if XE drivers are loaded: lsmod | grep xe I'll update as I work through this...