FINIK | GPU・グラボ

AI hardware, GPUs & datacenters. The machines behind your ChatGPT prompt. Sometimes it works.
グラボ・AI・自作PCの話題を英語で発信しています。

[FINIK | GPU・グラボ @Ruslan_BJ]

TWO RTX 5090s. BOTH MELTED.

Both ran AI models 24/7 at full load.

The connector wasn't even the hottest part.
The thermal cam found 92°C right next to it.

The fix cost less than a pizza.

[FINIK | GPU・グラボ @Ruslan_BJ]

@7GHz And the GPU side of it: 4K is 4× the pixels of FHD. Most people on Full HD aren't behind, they just didn't want to pay for a GPU that can push that.

[FINIK | GPU・グラボ @Ruslan_BJ]

@taki_pc_1115 The catch is that the CPU is soldered. Great value today, but there's no upgrade path later, the board and the chip live and die together.

[FINIK | GPU・グラボ @Ruslan_BJ]

@W_Yoshizaki ありがとうございます！

[FINIK | GPU・グラボ @Ruslan_BJ]

@rsensui Do you also run local models on that Mac Studio? An iPad as the front end for a home LLM box sounds perfect.

[FINIK | GPU・グラボ @Ruslan_BJ]

@epi_x Make it a curtain. Speakers you can't see, and the whole window plays music. Sound comes from fabric (4th time).

[FINIK | GPU・グラボ @Ruslan_BJ]

@MacroWorld21 MX23J12808 is a custom Macronix mask ROM made for Nintendo, so no public datasheet. The protection isn't in the chip, it's in the cartridge protocol (KEY1/KEY2 encryption). GBATEK documents all of it.

[FINIK | GPU・グラボ @Ruslan_BJ]

@Isichan_Hitori Interesting split between refusal and evasion. Removing the refusal direction fixes the obvious part, but evasion is spread across the whole model, so retraining the answering style makes sense.

[FINIK | GPU・グラボ @Ruslan_BJ]

@sinovoip Meanwhile in Japan, 1GB Raspberry Pis cost almost ¥9,000. A 32GB RK3588 board suddenly looks like a bargain.

[FINIK | GPU・グラボ @Ruslan_BJ]

@Yacamochi_db This is exactly what multi-GPU LLM builds need. A slot can look like x16 and still run at x4 through the chipset, and you only find out after the second card is in.

[FINIK | GPU・グラボ @Ruslan_BJ]

@PCONES Small note: SUPRIM is MSI's lineup, not ASUS. Looks like the shop tag got it mixed up too.

[FINIK | GPU・グラボ @Ruslan_BJ]

@sozoraemon The Pi 3 B+ costing more than a Pi 5 is wild. At that point the newer board is the only sane pick.

[FINIK | GPU・グラボ @Ruslan_BJ]

Running your own AI in the office sounds simple.
This is what it actually takes.
Dual Xeon, 64GB ECC sticks in every slot, and a wall of NVIDIA GPUs.
No cloud, no data leaving the building.
社内でAIを動かすなら、これくらい必要。
#ローカルLLM #自作PC

[FINIK | GPU・グラボ @Ruslan_BJ]

@hokazuya Honestly the most productive impulse buying I've ever seen. And B300 would be the logical next step: 288GB of HBM3e at around 8TB/s.

[FINIK | GPU・グラボ @Ruslan_BJ]

@Tono_Ken3 14kWh at ~480W is about 29 hours of full inference. Two days works if it spends part of the time idling.

[FINIK | GPU・グラボ @Ruslan_BJ]

@gollirapanty Most of that price jump is RAM. AI data centers are eating the DRAM supply, so DDR5 got hit the hardest.

[FINIK | GPU・グラボ @Ruslan_BJ]

@Hikari_07_jp Same open frame mining rigs used, just with 96GB cards and LLMs instead of Ethereum.For comparison, this is what a full DeepSeek V4 server looks like
https://t.co/zE6v3YhMBi

[FINIK | GPU・グラボ @Ruslan_BJ]

Turn your sound on. Chinese GPU mining farm, March 2021.

Thousands of cards running Ethereum nonstop, in a building that sounds like a jet engine. GPU shortage, scalper prices, empty shelves. You remember.

Two months later China banned mining. A year after that Ethereum dropped GPUs completely with the switch to proof of stake. Farms like this one just disappeared.

Fast forward to 2026 and we're doing the exact same thing again. Warehouses packed with GPUs, power grids struggling, gamers priced out. Only now it's AI instead of crypto.

Different coin, same racks.

[FINIK | GPU・グラボ @Ruslan_BJ]

@jpmyrmecol Does it need a GPU to run, or can it handle long videos on a regular PC?

[FINIK | GPU・グラボ @Ruslan_BJ]

@R3000C Different goals though. Apple builds one huge core for laptop speed, Arm puts 136 of these cores into one 300W server chip.