Inference › Optimization & Performance › Quantization v
quant choices for 70B local on GB200

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
quant choices for 70B local on GB200
cobalttinker Offline
Member
***
Posts: 52
Threads: 4
Joined: Sep 2026
Reputation: 0
#2
10-13-2026, 04:51 AM
Quote:Curious what people here are seeing.

Tried to reproduce it just now. I couldn't reproduce the slowdown until I pushed context much higher. The surprise was that memory pressure showed up before throughput collapsed.
Find
Reply


Messages In This Thread
Re: quant choices for 70B local on GB200 - by cobalttinker - 10-13-2026, 04:51 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)