dreamstick

Building -

[dreamstick @DREAMSTICK4]

Dude I feel so bad for Switzerland 😭

[dreamstick @DREAMSTICK4]

@Abhinavstwt @abhinavexists_ Hey, I am really interested, could you also teach me please...?

[dreamstick @DREAMSTICK4]

Building + Watching the World Cup at 1:54 am,
Life can't get better!

[dreamstick @DREAMSTICK4]

Now that Antigravity has reduced it's Limits so much, I realize that now we can't just Use tokens like how we used to before, Thinking of a very big project? Well now either you are forced to pay or just have to go with some 9b local model that has a very small context window 😭

[dreamstick @DREAMSTICK4]

@rakshit_yadav19 Nah bhai why wait for 2027, Half the year is still left 📈

[dreamstick @DREAMSTICK4]

@TarunyaKesh Well, my friend has an O'reilly subscription that I'm borrowing, but you can use Anna's archive to get the pdf if you want!

[dreamstick @DREAMSTICK4]

Read the first 2 chapters of this book today, and I can confidently say that I can explain RAG to anyone now, no matter what is the background!! 😆

[dreamstick @DREAMSTICK4]

@spirit_194 Nice buddy keep it up!!

[Jun Song @jun_song]

Local AI 101 - Models by Parameter Size

The 'B' stands for Billion parameters. A good rule of thumb is 1B = roughly 1GB of VRAM.

~1B (Nano): Used for specific simple tasks like OCR, or built into web apps for lightweight execution.

~9B (Micro): Convenient as a support model running on small hardware like smartphones or laptops.

~35B (Mini): The sweet spot for standard consumer devices. Once fine-tuned, they perform specific tasks very well.

~400B (Haiku size): Includes lightweight models like Deepseek V4 Flash and Minimax M3. The max size runnable on a single 128GB Mac using dynamic quant.

~800B (Sonnet size): Mid-size models like GLM-5.2 and Kimi. Requires 512GB+ VRAM, but excellent for complex tasks like coding.

1.6T+ (Opus size): Massive models like Deepseek V4 Pro and Longcat. Too heavy for consumer devices; requires server-grade hardware.

[dreamstick @DREAMSTICK4]

https://t.co/ULYiO7r50X

[dreamstick @DREAMSTICK4]

@spirit_194 @spirit_194 Nice man, keep going!

[dreamstick @DREAMSTICK4]

@rakshit_yadav19 @claudeai be safe bro, ek darinda aa rha hai tere pas

[dreamstick @DREAMSTICK4]

Yay, I have uploaded my rag app as an image to dockerhub, check it out :- https://t.co/o2Ms4RnrUo

Next step:- Deploy to kubernetes

[dreamstick @DREAMSTICK4]

YESS, Now finally my Rag-api got converted into a docker image (im sure 'converted' is the right word) and also the container works!!

[dreamstick @DREAMSTICK4]

@rakshit_yadav19 All the best bro!!

[dreamstick @DREAMSTICK4]

Today I'm going to containerize my RAG api with docker

[dreamstick @DREAMSTICK4]

@rakshit_yadav19 ok ok mai baitha hu

[dreamstick @DREAMSTICK4]

@rakshit_yadav19 kb hai?