Tried. The context windows just weren't big enough.

coder543 3 hours ago | parent | next [-]

Qwen3.6-27B supports a 1 million token context window.

Of course, you have to have the right hardware to be able to run with a context window like that, as it takes about 100GB of memory on my DGX Spark to do that with full f16 KV cache on the q4_k_xl model.

▲

lysace 5 hours ago | parent | prev | next [-]

Got a similar result (my RTX 4070 only has 12 GB). I'm curious about whether 24/32 GB meaningfully improves this enough to make it useful.

▲

tobyhinloopen 5 hours ago | parent [-]

Try it on RAM and CPU.

It’s slower but you can run them.

	▲	lysace 4 hours ago \| parent [-]
		Good idea for evaluating the models, thanks.

▲

deadbabe 5 hours ago | parent | prev [-]

Prompt more directly instead of open ended.