Inference › Edge AI & Gadgets › Mobile
mobile NPU reality check

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
mobile NPU reality check
marbleyard32 Offline
Junior Member
**
Posts: 30
Threads: 3
Joined: Sep 2026
Reputation: 0
#1
10-06-2026, 12:38 AM
Spent some time on this today and wanted to compare notes.

I've gone back and forth between TensorRT-LLM and llama.cpp for Mistral. The interesting difference for me has been quant drift.

Interested in tradeoffs more than fan loyalty.
Find
Reply


Messages In This Thread
mobile NPU reality check - by marbleyard32 - 10-06-2026, 12:38 AM
Re: mobile NPU reality check - by cudacrate - 10-06-2026, 04:49 AM
Re: mobile NPU reality check - by torchkite - 10-06-2026, 05:56 AM
Re: mobile NPU reality check - by cozysmith - 10-06-2026, 10:15 AM
Re: mobile NPU reality check - by relaysupply90 - 10-07-2026, 10:38 PM
Re: mobile NPU reality check - by promptspark58 - 10-08-2026, 03:00 AM
Re: mobile NPU reality check - by llmpeak - 10-08-2026, 04:10 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)