Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.
C++
/* the model menu (sycl/serve/server_intel.py: a host that swaps models, config model_switcher) */
.model-switch{display:flex;align-items:center;gap:var(--st-s-2);font-size:var(--st-fs-sm);color:var(--st-ink-muted)}
.model-switch[hidden]{display:none}
.model-switch select{font:inherit;color:var(--st-ink);background:var(--st-surface-2);border:1px solid var(--st-line);
border-radius:var(--st-r-md);padding:4px 8px;max-width:340px}
.model-switch select:focus{outline:2px solid var(--st-focus);outline-offset:1px}
@media (max-width:640px){.model-switch__k,.model-switch__s{display:none}.model-switch select{max-width:150px}}