Inference › Inference Engines › Other Engines v
NVFP4 / INT4 tradeoffs for Mistral

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
NVFP4 / INT4 tradeoffs for Mistral
mintstream9 Offline
Junior Member
**
Posts: 26
Threads: 1
Joined: Sep 2026
Reputation: 0
#2
09-30-2026, 01:38 AM
A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at prefill/decode split. Once you know the plain path works, then add the faster path back in piece by piece.
Find
Reply


Messages In This Thread
Re: NVFP4 / INT4 tradeoffs for Mistral - by mintstream9 - 09-30-2026, 01:38 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)