the qwen flash next result is the actual interesting part. The 27b dense model has more active parameters than, e.g. latest deepseek flash.

▲

SwellJoe 2 hours ago | parent [-]

For folks with 128GB inference machines that's definitely the more interesting model. 27B is dog slow on a Strix Halo. And, while Qwen 3.8 Flash is quite snug in 128GB at four bits (a bit more comfortably at three bits, but intelligence is really dropping by then) but is notably faster than the dense model. It thinks a little less and thinks a little faster, adding up to a real improvement. At four bits, it feels a little bit smarter than 27B even at eight.

If someone has one or two 32GB GPUs with decent bandwidth (faster than the Strix Halo or DGX Spark), the dense model is the obviously better choice, and I think that case is more common for the average developer.

▲

sureglymop 2 hours ago | parent [-]

I've been running Qwen 3.8 Flash Next on Strix Halo with halogen-flash-server which is a pretty good experience (although unfortunately halogen is closed source).

But for coding and cybersec tasks I think GLM 5.3 might be the best one to use still.

	▲	SwellJoe 2 hours ago \| parent [-]
		Nobody's running GLM 5.3 on a Strix Halo. But, yes, I'm using cloud models for everything hard, including coding. I use local models for smaller API tasks or sub-agent tasks and experiments with fine-tuning and benchmarking.