NewsLab
Apr 28 22:14 UTC

Intel Arc Pro B70 Review (pugetsystems.com)

56 points|by zdw||26 comments|Read full story on pugetsystems.com

Comments (26)

24 shown
  1. 1. 100ms||context
    These seem amazing for hobbyist, but that TDP given the perf might be an issue deploying a lot of them
  2. 2. zrm||context
    Its performance is pretty unbalanced. If you're using it for the couple of things that it's good at, the TDP is competitive.
  3. 3. tempest_||context
    I would like one for the vram but I am sure they will be unobtainable after the initial stock sells out as I assume they were produced before the RAM prices went up.
  4. 4. XCSme||context
    Can you use those AI cards for gaming too?

    Or the makers intentionally nerf them, in order to better segment the markets/product lines?

  5. 5. ZiiS||context
    The drivers often need per game optimisations these will be missing but I doubt Intel would nerf them, just rely on you not paying a lot for RAM the game won't use.
  6. 6. XCSme||context
    I actually meant it in a different way. I would get it for local AI stuff, but being able to game on it would be a huge plus, otherwise I would need two different machines.
  7. 7. wmf||context
    They nerf gaming cards to make money on the pro cards. Since this is a pro card it's not nerfed.
  8. 8. MostlyStable||context
    Is Intel still making GPUs? I have heard so many conflicting things about will they/won't they stay in the market.
  9. 9. dismalaf||context
    They'll always have iGPUs so whether or not they stay in the dGPU market depends mostly on whether or not people buy them. So they might not, whole market seems to be moving to SoCs/APUs/whatever you want to call them.
  10. 10. 2OEH8eoCRo0||context
    I don't know what to believe when it comes to Intel news because they have so many haters.
  11. 11. numpad0||context
    Intel always had that habit of starting an internal conflict whenever whatever potential alternative revenue sources start to threaten their internal dependence on x86
  12. 12. speedgoose||context
    Time to first token is a very important performance metric, as I figured out using a Mac Studio M3 Ultra (that is quite slow on this aspect).

    But 32GB for a TDP of 230W is perhaps not super interesting. Especially because you probably want to have more than one card. It's a lot of heat. You could use the cards for heating up a building, but heatpumps exist.

  13. 13. bigyabai||context
    A lot of the TDP is reserved for running the shader units at full-power. My RTX 3070 Ti only pulls ~110w of it's 320w running CUDA inference on Gemma 26b and E4B.
  14. 14. Scaevolus||context
    It's not that it's reserving power, but rather that you hit some bottleneck on a 3070 Ti before running into thermal limits-- it's likely limited by either tensor core saturation or RAM throughput. Running the workload with Nvidia's profiling tools should make the bottleneck obvious.
  15. 15. lambda||context
    Generally the bottleneck is RAM throughput. Inference, in particular token generation, especially on a single user instance, is not all that computationally complex; you're doing some fairly simple calculations for each parameter, the time is dominated by just transferring each parameter from RAM to the cores. A 31B dense model like Gemma 4 has to transfer 31B parameters (at 16 bits per parameter for the full model, though on consumer hardware people generally run 4-8 bit quantizations) from RAM to the cores, that's a lot of memory transfer.

    Prompt processing or parallel token generation can do a bit more work per memory transfer, as you can use the same weights for a few different calculations in parallel. But even still, memory bandwidth is a huge factor.

  16. 16. SparkyMcUnicorn||context
    Here are some llama.cpp benchmarks for it: https://www.phoronix.com/review/intel-arc-pro-b70-linux/3
  17. 17. zargon||context
    Also from phoronix, a comparison with AMD R9700 and RTX 6000 Ada (because Nvidia has not sent them a blackwell card): https://www.phoronix.com/review/intel-arc-pro-b70/2
  18. 18. driverdan||context
    From what I've read the Intel drivers are terrible and holding back using them for LLMs.
  19. 19. 999900000999||context
    Everyone has terrible drivers here aside from Nvidia.

    Intel looks like they'll leave the dedicated GPU space, so it's a bit doubtful if the drivers will ever catch up.

  20. 20. martinald||context
    Don't think that's true. The drivers are bad (not sure terrible is fair, they have improved a lot) esp for older directx etc games. But Vulkan support is pretty good and that's all you need for LLMs really.
  21. 21. marshray||context
    I don't know about LLMs, but I tried an Intel card when Ubuntu Wayland couldn't initialize a 2 year old Nvidia. It just works.
  22. 22. cubefox||context
    Why are they still using their old Xe2/Battlemage architecture rather than their new Xe3/Celestial? They already used it in their Panther Lake chip set.
  23. 23. numpad0||context
    [delayed]
  24. 24. kinow||context
    For those that use Blender, in their section about Blender:

    > We hope that, in the future, there will be real options other than NVIDIA for GPU-based rendering, as it is an area where competition is nearly non-existent.

    And Checking opendata.blender.org, a NVIDIA GeForce RTX 4080 Laptop GPU scores 5301.8, while Intel Arc Pro B70 is still at 3824.64.

    So there is still a bit more to go before Intel GPUs perform close to NVIDIA's.