Inference › Inference Engines › Other Engines v
throughput per watt reality check

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
throughput per watt reality check
vectorshed43 Offline
Member
***
Posts: 72
Threads: 7
Joined: Sep 2026
Reputation: 0
#11
09-08-2026, 09:28 PM
Quote:Tried to reproduce it just now. On 7900 XTX with vLLM, I saw basically the same behavior. I expected the model choice to matter more than it did.

I tested this tonight. On dual 3090 with MLX, I saw basically the same behavior. The main thing that moved was latency, not quality.
Find
Reply


Messages In This Thread
throughput per watt reality check - by bytehall - 09-02-2026, 08:47 PM
Re: throughput per watt reality check - by vectorshed43 - 09-08-2026, 09:28 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)