Skip to content

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++

Models screen: DeepSeek is installed and shown at its one 8K context (as the guided setup), not the 32K default

Niko1221ad66a758a7bd
diff --git a/apps/host/src/components/NativeModels.tsx b/apps/host/src/components/NativeModels.tsx
index 4bf16382c..1a2bcba61 100644
--- a/apps/host/src/components/NativeModels.tsx
+++ b/apps/host/src/components/NativeModels.tsx
@@ -104,7 +104,7 @@ export function NativeModels({ onOtherModels, onReady, onImport, onConnectEngine
// Drafting (which drafter guesses ahead): DFlash2 is for Qwen3.8-Flash-Next only (the qwen and gyro families), so no other model is offered it.
const draftingChoices = selectedSize ? draftingOptions(selectedSize.sourceFamily ?? selectedFamily?.family, native?.capabilities?.dflash2) : null;
const draftingWords: Record<string, string> = { auto: 'Auto (recommended)', mtp: 'MTP', dflash2: 'DFlash2', off: 'Off' };
- const values = useMemo(() => ({ family: selectedSize?.sourceFamily, model: selectedSize?.model, context, vision: selectedSize?.images ? vision : 'no', kv, low_ram: lowRam, resourceProfile, ...(cardsGpus.length > 1 ? { gpus: cardsGpus.join(',') } : cardsGpus.length === 1 ? { gpu: cardsGpus[0] } : {}), loadAfter: true, multiple: expert && multiple }), [selectedSize?.sourceFamily, selectedSize?.model, context, vision, kv, lowRam, resourceProfile, cardsGpus.join(','), expert, multiple]);
+ const values = useMemo(() => ({ family: selectedSize?.sourceFamily, model: selectedSize?.model, context: selectedSize?.multi_file ? 8192 : context, vision: selectedSize?.images ? vision : 'no', kv, low_ram: lowRam, resourceProfile, ...(cardsGpus.length > 1 ? { gpus: cardsGpus.join(',') } : cardsGpus.length === 1 ? { gpu: cardsGpus[0] } : {}), loadAfter: true, multiple: expert && multiple }), [selectedSize?.sourceFamily, selectedSize?.model, context, vision, kv, lowRam, resourceProfile, cardsGpus.join(','), expert, multiple]);
const downloadValues = { ...values, ...(draftingChoices ? { drafting } : {}), vision: selectedSize?.images && vision !== 'no' ? 'yes' : 'no', loadVision: selectedSize?.images ? vision : 'no' };
useEffect(() => { if (!native?.catalog || family)
return; const current = native.instances.find(i => i.id === native.defaultId); const rec = native.catalog.recommendation ?? { family: null, model: null }; const loadedFamily = families.find(f => f.sizes.some(s => s.id === current?.model)); const have = new Set((native.installed?.models ?? []).filter(m => m.ready).map(m => m.model)); const installedFamily = families.find(f => f.sizes.some(s => have.has(s.id))); const f = loadedFamily ?? installedFamily ?? families.find(f => f.family === rec.family || f.sizes.some(s => s.sourceFamily === rec.family)) ?? families[0]; if (f) {
@@ -138,8 +138,11 @@ export function NativeModels({ onOtherModels, onReady, onImport, onConnectEngine
if (installed.resourceProfile && !loadedSelected?.resourceProfile)
setResourceProfile(installed.resourceProfile);
}
- else
+ else {
setVision('yes');
+ if (selectedSize.multi_file)
+ setContext(8192); // DeepSeek runs at the one context its engine was checked at (as in the guided setup)
+ }
}, [selectedSize?.id, installed?.model, installed?.ready, installed?.context, installed?.kv, installed?.images, installed?.visionEnabled, installed?.visionDevice, installed?.lowRamMode, installed?.resourceProfile]);
useEffect(() => { if (jobId && job?.state === 'done' && job.id !== toastedJob && (job.kind === 'load' || job.kind === 'install')) {
setToastedJob(job.id);