LMSYS published the real Qwen3.8-Flash-Next deployment numbers, and offloading the n-gram table frees 23.46 GiB per GPU.

The day-0 SGLang post dated August 26 gives the architecture the release megathread didn't: 125B main parameters plus a separate 51.2B Per-Layer Embedding table at about 95.4 GiB in BF16, 6B activated per token, 48 layers split 36 GDN linear attention and 12 QSA sparse attention, 512 experts with top-10 routing (LMSYS). Sparse pinned-host offload of the PLE table on H200 with TP4 drops weight footprint per GPU from 83.91 to 60.45 GiB and raises KV cache capacity from 1.84M to 3.28M tokens, a 78.5% increase. On B200 TP4 with MTP speculative decoding it reaches 540 tok/s at batch size 1 with an accept length of 3.3.