Qwen3.8 125B (6B active) Flash-Next
on 2× AMD Radeon AI PRO R9700 32GB · vLLM-Radiance · 131,072 ctx
Use cases
visionlong-context
Summary
User reports custom kernels for RDNA4 giving roughly 3x generation speedup and roughly 30x prefill speedup over public vLLM-Radiance.
Setup is dual R9700s with 128GB RAM.
User also mentions work on the Muse Glimmer 30B dense model.