Inference › Optimization & Performance › Quantization v
best small quant that still feels smart on 4090

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
best small quant that still feels smart on 4090
vrambandit Offline
Member
***
Posts: 168
Threads: 14
Joined: Sep 2026
Reputation: 0
#2
10-06-2026, 12:05 AM
I tested this tonight. On GB200 with MLX, I saw basically the same behavior. I expected the model choice to matter more than it did.
2x3090 • llama.cpp • too much VRAM is still not enough
Find
Reply


Messages In This Thread
Re: best small quant that still feels smart on 4090 - by vrambandit - 10-06-2026, 12:05 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)