I do love using local models when I can, but qwen-35B is the best model I can run, and while its an insanely good local model, it does not compare to the big ones.

▲

deaux 5 hours ago | parent [-]

Have you tried the latest Gemma? You might prefer it to Qwen, depending on what you're doing.

	▲	kanemcgrath 4 hours ago \| parent [-]
		I did, but in almost everything I tried even qwen3.5 was better, and 3.6 was a huge step up.