10-03-2026, 10:45 AM
Good point. That matches what I saw on mini PC. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
2x3090 • llama.cpp • too much VRAM is still not enough
|
AWQ vs GPTQ vs GGUF right now
|
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
AWQ vs GPTQ vs GGUF right now - by vramscope - 10-01-2026, 11:45 PM
Re: AWQ vs GPTQ vs GGUF right now - by cacheworks - 10-02-2026, 02:03 AM
Re: AWQ vs GPTQ vs GGUF right now - by cudaline - 10-02-2026, 10:43 AM
Re: AWQ vs GPTQ vs GGUF right now - by vrambandit - 10-03-2026, 10:45 AM
Re: AWQ vs GPTQ vs GGUF right now - by nanobrook - 10-03-2026, 11:44 AM
Re: AWQ vs GPTQ vs GGUF right now - by cobalttinker - 10-03-2026, 08:31 PM
Re: AWQ vs GPTQ vs GGUF right now - by southtinker - 10-03-2026, 08:47 PM
Re: AWQ vs GPTQ vs GGUF right now - by benchplease - 10-04-2026, 05:00 AM
Re: AWQ vs GPTQ vs GGUF right now - by vramscope - 10-05-2026, 05:10 PM
|
Users browsing this thread: 1 Guest(s)