Qwen3.8 125B (6B active) Flash-Next

on NVIDIA RTX 5090 · Strata · 131,072 ctx

Oct 29, 2026

Throughput

236.0 t/s gen · 6272.0 tokens/s prompt processing (prefill)Prompt processing measures input prefill speed; it does not tell you the time to first token.

Quant

IQ3_S (GGUF)

KV cache

int8

VRAM reported

32 GB

Summary

User reports Qwen3.8-Flash-Next at 236 tok/s decode and 6,272 tok/s prefill on an RTX 5090, upgraded from an RX 9070 XT. Setup is Strata Engine 0.1.52 with IQ3_S GGUF weights, int8 KV cache, 128K context, MTP speculation with spec=4, and adaptive VRAM/RAM expert caching. The user presents this as a head-to-head against the previous 16GB ROCm card.

View source ↗