Use cases
codingagentic
Summary
User reports Qwen3.8 Flash-Next at up to 275 tok/s peak generation and 5500 tok/s prompt processing on a single RTX 5080 16GB with 64 GB DDR5-6400 and a Core Ultra 9 285K.
Setup is the Strata fork Basalt with IQ3_S weights, run during a live opencode coding session.
Code and tool calls peak at 275 tok/s while reasoning traces reach up to 190 tok/s; the user says the IQ3_S quant is very usable.