HackerTrans
TopNewTrendsCommentsPastAskShowJobs

Readerium

no profile record

comments

Readerium
·10 दिन पहले·discuss
3.5 Pro not yet launched, you mean 3.1 pro?
Readerium
·पिछला माह·discuss
Loll
Readerium
·2 माह पहले·discuss
For MSFT: Just download DeepSeek locally and use it.

Or train your own power efficient stack.
Readerium
·2 माह पहले·discuss
AI workloads are all about memory size and bandwidth not compute
Readerium
·2 माह पहले·discuss
LLMs are memory bandwidth bound not compute bound.
Readerium
·3 माह पहले·discuss
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 माह पहले·discuss
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 माह पहले·discuss
perhaps increasing repitition_penalty might be helpful
Readerium
·3 माह पहले·discuss
In coding they are worse.

Chinese models (GLM, MiniMax) are better.
Readerium
·4 माह पहले·discuss
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 माह पहले·discuss
Qwen 3.5 4B is the goat then
Readerium
·4 माह पहले·discuss
Yes he is room-mates with.
Readerium
·9 माह पहले·discuss
99.999 percent lol
Readerium
·10 माह पहले·discuss
So was intel in the following sentence.
Readerium
·10 माह पहले·discuss
[dead]