Hacker News: ycui7

New comment by ycui7 in "Intel Arc Pro B70 Review"

ycui7 — Wed, 29 Apr 2026 07:45:21 +0000

Exiting dGPU for gaming, but staying in the LLM world.

New comment by ycui7 in "Intel Arc Pro B70 Review"

ycui7 — Wed, 29 Apr 2026 07:42:37 +0000

B70 idles at 30W, while RTX PRO 4500 idles at 9W (measured to be 5W at wall).

B70 runs at 1/3 token output rate of RTX PRO 4500 and consume 3X idle power when do nothing.

New comment by ycui7 in "Intel Arc Pro B70 Review"

ycui7 — Wed, 29 Apr 2026 07:37:05 +0000

When you get 4 of these, the idle power alone is 120W. That is a lot of electricity if left on 24/7.

At that power consumption, you also end up being more expensive than API calls and many times slower. It starts to feel very stupid to run local interference.

If the client is very keen on privacy, then they can pay for the NVIDIA.

I end up returning my B70s, and bought RTX PRO 6000.

New comment by ycui7 in "Intel Arc Pro B70 Review"

ycui7 — Wed, 29 Apr 2026 07:31:12 +0000

At this speed, people end up paying more on electricity than api calls. (California electricity)

New comment by ycui7 in "Intel Arc Pro B70 Review"

ycui7 — Wed, 29 Apr 2026 07:28:59 +0000

You can get 120TPS (144 peak) with Qwen3.6-27B on RTX PRO 6000 with autoround when MTP enabled. It runs faster than sonnet api calls.

5090 gets maybe 100TPS with MTP

New comment by ycui7 in "Intel Arc Pro B70 Review"

ycui7 — Wed, 29 Apr 2026 07:25:13 +0000

Problem is the more B70 you have, the slower the inference it gets(due to terrible software atm). A single B70 is almost barely faster than CPU inference. If you have 4 B70, you might as well run interference on CPU and be faster with cheaper DDR5 instead of GDDR6.

New comment by ycui7 in "Intel Arc Pro B70 Review"

ycui7 — Wed, 29 Apr 2026 03:32:04 +0000

Intel Arc B70 when released, can only produce 1/3 of the token of RTX PRO 4500. Well, it also cost 1/3 of RTX PRO 4500.

It lacked software support the for the primary target application, running LLM. The officially supported vllm fork is 6 version behind mainline. It did not run the latest hot new open models on huggingface. Parallel two of B70 reduce token rate, not improve it. So, the software behind B70 is basically so far behind.

New comment by ycui7 in "Intel Arc Pro B70 Review"

ycui7 — Wed, 29 Apr 2026 03:28:40 +0000

It is weird that the reviewer does not mention RTX PRO 6000 96GB, but mentioned RTX PRO 5000 72GB. 72GB RTX PRO 5000 is a special order, and much less people are aware of it. RTX PRO 6000 is known by mostly everyone in the LLM world.

I cannot understand why would a tech reviewer do that.