How to run Qwen 3.5 locally

Re:How to run Qwen 3.5 locally by codemog on Sunday March 08, 2026 @04:51AM (#47295704)

Interesting. I see papers where researchers will finetune models in the 7 to 12b range and even beat or be competitive with frontier models. I wish I knew how this was possible, or had more intuition on such things. If anyone has paper recommendations, I’d appreciate it.

[ Parent | on HN ]

Re:How to run Qwen 3.5 locally by stavros on Sunday March 08, 2026 @06:08AM (#47296029)

They're using a revolutionary new method called "training on the test set".

[ Parent | on HN ]

Re:How to run Qwen 3.5 locally by drob518 on Sunday March 08, 2026 @02:34PM (#47299767)

So, curve fitting the training data? So, we should expect out of sample accuracy to be crap?

[ Parent | on HN ]

Re:How to run Qwen 3.5 locally by stavros on Sunday March 08, 2026 @02:47PM (#47299875)

Yeah, that's usually what tends to happen with those tiny models that are amazing in benchmarks.

[ Parent | on HN ]