Inference › Optimization & Performance › Quantization v
quant choices for 70B local with PyTorch

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
quant choices for 70B local with PyTorch
turbosupply83 Offline
Junior Member
**
Posts: 30
Threads: 3
Joined: Sep 2026
Reputation: 0
#7
10-18-2026, 08:19 PM
Quote:following this because I'm in the same boat.

A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at router policy. Not glamorous advice, but repeatable baselines save a lot of time.
Find
Reply


Messages In This Thread
Re: quant choices for 70B local with PyTorch - by turbosupply83 - 10-18-2026, 08:19 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)