Qwen3.8-Max: A New Bar for Coding and Cowork

Re:Qwen3.8-Max: A New Bar for Coding and Cowork by numpad0 on Monday August 03, 2026 @05:19AM (#49153249)

Yeah, here I am sitting deeply deeply deeply regretting not buying couple CMP 170HX at $200 or $350, knowing I could just flip them ethically at purchase price if nothing came of it... I could have just casually built a 128GB dual A100 local AI monster

[ Parent | on HN ]

Re:Qwen3.8-Max: A New Bar for Coding and Cowork by jimmySixDOF on Monday August 03, 2026 @07:57AM (#49154585)

I'm working with a lab that has a few Ampere GPUs on infiniband and they are just not compatible with the latest quants and vLLM updates. FP8 is about as low as you can go.

[ Parent | on HN ]

Re:Qwen3.8-Max: A New Bar for Coding and Cowork by numpad0 on Monday August 03, 2026 @12:38PM (#49158093)

But they're reportedly a soft nerfed GA100 64GB/40GB at $1200, that's not more expensive and certainly can't be slower than a Mac Studio.

[ Parent | on HN ]