Qwen3.8-27B - Hackdot

Re:Qwen3.8-27B by hadlock on Friday August 14, 2026 @04:00PM (#49303863)

For high concurrency, using the blackwell's native native W4A4 MLP compute path, nvfp4 is something like a 1.2-1.5x performance increase over FP8. We're doing data enrichment (so, tasks completed successfully + tokens/second) so the performance bump shows up in the tasks/month number.

I am just now getting the benchmarks running against 3.8 27b but I expect similar results from benching 3.6 27b at the same quant.

[ Parent | on HN ]

Re:Qwen3.8-27B by eblanshey on Friday August 14, 2026 @07:30PM (#49305844)

I see. Did you see any intelligence degradation between FP8 and NVFP4 for 3.6 27B? You're using vLLM, right?

[ Parent | on HN ]

Re:Qwen3.8-27B by hadlock on Monday August 17, 2026 @01:33AM (#49326881)

I didn't have time to run this as well, but we're getting a 99% agent completion rate across all tasks and 98% task decision that matches the human selected option(s) on Qwen 3.8 27B @ NVFP4. There may be a difference between FP8 and NVFP4 but it's inconsequential for our data enrichment purposes.

[ Parent | on HN ]