Coding expertise is going to collapse from AI reliance

Re:Coding expertise is going to collapse from AI reliance by ex1fm3ta on Tuesday August 25, 2026 @02:49PM (#49438751)

hmm that's a bit low right now, since you need at least 48Gb of VRAM to be confortable. 32Gb might do it (on quantitized models + optimized) but it would be very slow.

[ Parent | on HN ]

Re:Coding expertise is going to collapse from AI reliance by lrvick on Tuesday August 25, 2026 @11:41PM (#49443972)

That may have been true a few months ago, but shit changes fast in this space!

I run Qwen 3.8 27b on each of my six AMD AI PRO r9700 GPUs at 80tps decode each and they cranks for days with 256k context, doing complex kernel, compiler, debugging, enclave, bootstrapping, pentesting, hardening, and systems work full time.

~$1200-1500/ea on ebay.

Also ~40tps on my strix halo now but with room for several sessions at once.

[ Parent | on HN ]

Re:Coding expertise is going to collapse from AI reliance by nicce on Wednesday August 26, 2026 @07:58AM (#49447464)

What is your config for getting 80tps decode?

[ Parent | on HN ]

Re:Coding expertise is going to collapse from AI reliance by lrvick on Wednesday August 26, 2026 @04:44PM (#49455637)

Qwen 3.8 27b Q4_K_M w/ matching dflash drafter, 256k context, llama.cpp+dflash2, draft-n-max=5

Also using with Charmbracelet Crush with Froggerinc fixed chat templates.

[ Parent | on HN ]

Re:Coding expertise is going to collapse from AI reliance by nicce on Thursday August 27, 2026 @05:41AM (#49462116)

Thank you! Have to look into it.

[ Parent | on HN ]