Readerium · HackerTrans

Readerium

10 gün öncediscuss

3.5 Pro not yet launched, you mean 3.1 pro?

Readerium

geçen aydiscuss

Loll

Readerium

2 ay öncediscuss

For MSFT: Just download DeepSeek locally and use it.

Or train your own power efficient stack.

Readerium

2 ay öncediscuss

AI workloads are all about memory size and bandwidth not compute

Readerium

2 ay öncediscuss

LLMs are memory bandwidth bound not compute bound.

Readerium

3 ay öncediscuss

Add an iPad mini esque screen on the trackpad of a MacBook.

Trackpad of a 16 inch MacBook Pro is humongous anyways.

Add a touchscreen display to the trackpad, and give it iPad OS

Readerium

3 ay öncediscuss

that is true. gguf does not support any Architecture.

for the most recent example, as of April 16, 2026 (today)

Turboquant isnt still added to GGUF

Readerium

3 ay öncediscuss

perhaps increasing repitition_penalty might be helpful

Readerium

3 ay öncediscuss

In coding they are worse.

Chinese models (GLM, MiniMax) are better.

Readerium

4 ay öncediscuss

Can someone explain if the 3D Vcache are stacked on top of each other or side by side.

If they are stacked then why not 9800X3D2?

Readerium

4 ay öncediscuss

Qwen 3.5 4B is the goat then

Readerium

4 ay öncediscuss

Yes he is room-mates with.

Readerium

9 ay öncediscuss

99.999 percent lol

Readerium

10 ay öncediscuss

So was intel in the following sentence.

Readerium

10 ay öncediscuss

[dead]

comments