🦊🐱 fur account：@scarffurry • 🎨 cms open：https://teapawt.net/t.co/uMA0UhO1NC • 📦 FANBOX：https://teapawt.net/t.co/xDurIG2yJK • 💬 TH ⁄ EN：OK｜Other ⁄ 他：Translator ⁄ 翻訳
anti-depressant pill boxes
Joined March 2009
- Tweets21K
- Following1.5K
- Followers8.7K
- Likes6K
Pinned Tweet
🌟 My commissions on #VGen are now open 🌟
vgen.co/korstudio
🟢Cel-shade Commission - 5 slots
• Price: From $50.00
• Style: Skeb / Surprise Me (Draw in my style)
• Just write your details and attach reference links.
👉 vgen.co/korstudio/service/pr…
🟢Profile Picture - 10 slots
• Price: $20.00
• Cel-shade, solid color and transparent background
👉 vgen.co/korstudio/service/in…
cc: @_VGen_
#VGenCommission #CommissionsOpen #ArtCommission
ＫＯＲ 🧑💻🎨 • 🔜 BangkokBeasts 2026 retweeted
Terrorizing the neighborhood with @berryshrimpus
Art by @kuuroo002789553
ＫＯＲ 🧑💻🎨 • 🔜 BangkokBeasts 2026 retweeted
I Agree with Sam Altman.
First of all, local models are useless, they're dumb and slow
You'll spend ~$1000 on 128 GB RAM to run a local model
And you won't get anything done with it, dumb models at 8tps are useless
A $20 subscription will get more things done
And for 95% of the time, RAM is not being used so it's doing less work there compared to in a data centre where utility is more
Readers added context they thought people might want to know
Local models on suitable 128GB hardware often run at 30+ tokens/second and offer practical uses; 128GB DDR5 RAM kits currently start above $2200, not ~$1000.
datahardware.ai/tools/benchmar…
theramageddon.com/128gb-ddr5-ram…
ＫＯＲ 🧑💻🎨 • 🔜 BangkokBeasts 2026 retweeted
Trick-or-treat!
Give me some candy please🍬
Ych by @CodyPeryton
