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: GPU numbering matches the other screens, friendly model names, fit figures less what the kept models use
Niko1221201d674e94c3
diff --git a/apps/host/server/model-names.mjs b/apps/host/server/model-names.mjsnew file mode 100644index 000000000..084b91558--- /dev/null+++ b/apps/host/server/model-names.mjs@@ -0,0 +1,8 @@+/** The name a person reads for a loaded model: the family and the version from the catalog ("Qwen3.8-Flash-Next Q2_0"), not the file id. */+export function friendlyModelName(catalog, id) {+ for (const family of catalog?.families ?? []) {+ const size = (family.sizes ?? []).find(s => s.id === id);+ if (size?.model && family.title) return `${String(family.title).replace(/\s*\(Gyro\)\s*$/, '')} ${size.model}`.trim();+ }+ return null;+}diff --git a/apps/host/server/native-control.mjs b/apps/host/server/native-control.mjsindex 37a19d689..a7c1c8f94 100644--- a/apps/host/server/native-control.mjs+++ b/apps/host/server/native-control.mjs@@ -18,6 +18,7 @@ import { plainError, PHASE_TEXT } from './update-messages.mjs';import { checkRunConfig, describeIssues } from './run-config-check.mjs';import { openTextFile } from './open-text-file.mjs';import { markEngine, engineRefusal } from './engine-version.mjs';+import { friendlyModelName } from './model-names.mjs';const ROOT=resolve(dirname(fileURLToPath(import.meta.url)),'..');const safeId=value=>typeof value==='string'&&/^[a-z0-9_-]{1,80}$/i.test(value);@@ -222,7 +223,7 @@ return {summary:result.summary??'Deleted',removed:result.plan?.gb??null};}if(!args.multiple){if(busy(requests().filter(r=>instances.has(r.instanceId))))throw new Error('Finish or cancel native requests before switching models.');for(const id of [...instances.keys()])await unload(id);}else if(matching)await unload(matching.id);if(job.state!=='running')return;writeFileSync(configPath,JSON.stringify(cfg,null,2),{mode:0o600});- const instance={id,apiModelId,fingerprint,context:entry.context??0,aliases:cfg.aliases??[],vision:!!cfg.vision,resourceProfile:cfg.ui_resource_profile??null,model:args.model,label:entry.model_name??args.model,port:cfg.port,gpus:Array.isArray(cfg.gpu)?cfg.gpu:cfg.gpu===undefined?[]:[cfg.gpu],status:'loading',phase:'loading',parallel:cfg.parallel??1,mcpServers:cfg.mcp_servers??cfg.mcpServers??{},key,configPath,loadedAt:new Date().toISOString(),metrics:null,error:null};+ const instance={id,apiModelId,fingerprint,context:entry.context??0,aliases:cfg.aliases??[],vision:!!cfg.vision,resourceProfile:cfg.ui_resource_profile??null,model:args.model,label:friendlyModelName(snapshot.catalog,args.model)??entry.model_name??args.model,port:cfg.port,gpus:Array.isArray(cfg.gpu)?cfg.gpu:cfg.gpu===undefined?[]:[cfg.gpu],status:'loading',phase:'loading',parallel:cfg.parallel??1,mcpServers:cfg.mcp_servers??cfg.mcpServers??{},key,configPath,loadedAt:new Date().toISOString(),metrics:null,error:null};/* Another model on the same graphics card: the engine takes the card's free memory, so a second one usually finds none. Loading goes on (recommend, never force); if it fails, the reason is said. */const sharedWith=instance.gpus.length?[...instances.values()].find(i=>i.id!==id&&i.status!=='error'&&i.model!==args.model&&i.gpus.some(g=>instance.gpus.includes(g))):null;const sharedSentence=sharedWith?`GPU ${instance.gpus.find(g=>sharedWith.gpus.includes(g))+1} is already used by ${sharedWith.label}, so this model did not fit there. Load it on another GPU, or unload ${sharedWith.label} first.`:null;diff --git a/apps/host/src/components/ChatModelPicker.tsx b/apps/host/src/components/ChatModelPicker.tsxindex 5533bb96b..7389b90c5 100644--- a/apps/host/src/components/ChatModelPicker.tsx+++ b/apps/host/src/components/ChatModelPicker.tsx@@ -20,7 +20,7 @@ function NativeChatModelPicker() {const [open, setOpen] = useState(false), [error, setError] = useState('');const ref = useRef<HTMLButtonElement>(null);const current = native?.instances.find(i => i.id === native.defaultId);- return <><button className="chat-model-badge chat-model-picker" ref={ref} aria-label={tr("Choose model: {0}", [current?.label ?? 'Native model'])} aria-haspopup="menu" aria-expanded={open} onClick={() => setOpen(v => !v)}><Icon name="models" size={16}/><span>{tr(current?.label ?? 'Native model')}</span><Icon name="chevron" size={12}/></button>{tr(open ? <FloatingMenu anchor={ref.current} title={tr("Chat model")} width={340} onClose={() => setOpen(false)}>{tr(native?.instances.filter(i => i.status !== 'error').map(i => <button className="menu__item" role="menuitemradio" aria-checked={current?.id === i.id} disabled={streaming || i.status !== 'ready'} key={i.id} onClick={() => void nativeAction(`instances/${i.id}/default`).then(() => setOpen(false)).catch(e => setError(e.message))}><Icon name="models"/><span><strong>{tr(i.label)}</strong><small>{tr(i.apiModelId)} · {tr(i.gpus.map(g => `GPU ${g + 1}`).join(' + ') || 'Automatic GPU')}</small></span></button>))}{tr(providers?.connections.flatMap(c => c.models.map(m => <button className="menu__item" role="menuitem" disabled={streaming} key={`${c.id}-${m.id}`} onClick={() => { selectRemoteModel({ connectionId: c.id, modelId: m.id }); setOpen(false); }}><Icon name="link"/>{m.name} · {c.name}</button>)))}<button className="menu__item" role="menuitem" onClick={() => { setOpen(false); go('models'); }}>{tr("Manage models")}</button>{tr(error ? <p className="small inline-error">{tr(error)}</p> : null)}</FloatingMenu> : null)}</>;+ return <><button className="chat-model-badge chat-model-picker" ref={ref} aria-label={tr("Choose model: {0}", [current?.label ?? 'Native model'])} aria-haspopup="menu" aria-expanded={open} onClick={() => setOpen(v => !v)}><Icon name="models" size={16}/><span>{tr(current?.label ?? 'Native model')}</span><Icon name="chevron" size={12}/></button>{tr(open ? <FloatingMenu anchor={ref.current} title={tr("Chat model")} width={340} onClose={() => setOpen(false)}>{tr(native?.instances.filter(i => i.status !== 'error').map(i => <button className="menu__item" role="menuitemradio" aria-checked={current?.id === i.id} disabled={streaming || i.status !== 'ready'} key={i.id} onClick={() => void nativeAction(`instances/${i.id}/default`).then(() => setOpen(false)).catch(e => setError(e.message))}><Icon name="models"/><span><strong>{tr(i.label)}</strong><small>{tr(i.gpus.map(g => `GPU ${g + 1}`).join(" + ") || "Automatic GPU")}</small></span></button>))}{tr(providers?.connections.flatMap(c => c.models.map(m => <button className="menu__item" role="menuitem" disabled={streaming} key={`${c.id}-${m.id}`} onClick={() => { selectRemoteModel({ connectionId: c.id, modelId: m.id }); setOpen(false); }}><Icon name="link"/>{m.name} · {c.name}</button>)))}<button className="menu__item" role="menuitem" onClick={() => { setOpen(false); go('models'); }}>{tr("Manage models")}</button>{tr(error ? <p className="small inline-error">{tr(error)}</p> : null)}</FloatingMenu> : null)}</>;}function LegacyChatModelPicker() {const native = useNative();@@ -77,7 +77,7 @@ function LegacyChatModelPicker() {return <><button ref={trigger} className="chat-model-badge chat-model-picker" aria-label={tr("Choose model: {0}", [apiModel?.name ?? (running?.local ? running.name : running?.family) ?? 'No model loaded'])} title={tr(apiModel ? `${connection?.name} · ${apiModel.id}` : 'View and switch models')} disabled={!library && !providers} aria-haspopup="menu" aria-expanded={open} onClick={() => setOpen(v => !v)}><Icon name={apiModel ? 'link' : modelFamilyIcon(running?.family ?? groups[0]?.family)} size={16}/><span>{tr(apiModel?.name ?? (running?.local ? running.name : running?.family) ?? groups[0]?.family ?? 'No model loaded')}</span><Icon name="chevron" size={12}/></button>{tr(open ? <FloatingMenu anchor={trigger.current} title={tr("Models")} width={380} onClose={() => setOpen(false)}>- {tr(native?.instances.filter(i => i.status !== 'error').map(i => <button key={i.id} className="menu__item" role="menuitem" disabled={streaming || i.status !== 'ready'} onClick={() => void nativeAction(`instances/${i.id}/default`).then(() => { selectRemoteModel(null); setOpen(false); }).catch(e => setError(e.message))}><Icon name="models"/><span>{tr(i.label)}<small>{tr(i.apiModelId)}</small></span></button>))}<p className="model-picker-heading">{tr("Local models")}</p>+ {tr(native?.instances.filter(i => i.status !== 'error').map(i => <button key={i.id} className="menu__item" role="menuitem" disabled={streaming || i.status !== 'ready'} onClick={() => void nativeAction(`instances/${i.id}/default`).then(() => { selectRemoteModel(null); setOpen(false); }).catch(e => setError(e.message))}><Icon name="models"/><span>{tr(i.label)}<small>{tr(i.gpus.map(g => `GPU ${g + 1}`).join(" + ") || "Automatic GPU")}</small></span></button>))}<p className="model-picker-heading">{tr("Local models")}</p>{tr(!groups.length ? <p className="model-picker-empty">{tr("No local models downloaded yet.")}</p> : null)}{tr(groups.map(({ family, versions }, index) => {const main = versions[0], state = pickerVersionState(main, library!.loaded);diff --git a/apps/host/src/components/NativeModels.tsx b/apps/host/src/components/NativeModels.tsxindex 62b532529..b93440963 100644--- a/apps/host/src/components/NativeModels.tsx+++ b/apps/host/src/components/NativeModels.tsx@@ -50,7 +50,12 @@ export function NativeModels({ onOtherModels, onReady, onImport, onConnectEngine// This computer for the fit figures: the biggest usable graphics card, or the ones chosen under Expert settings.const pcGpus = (native?.hardware?.gpus ?? []).filter(g => g.usable !== false), pcGpu = [...pcGpus].sort((x, y) => y.vram_gb - x.vram_gb)[0] ?? null;const pcRam = native?.hardware?.ram_gb || hardware?.memory.totalGb || null, pcVram = pcGpu?.vram_gb ?? 0;- const fitHardware = { ram_gb: pcRam, vram_gb: pcVram };+ // What the models that stay loaded (Run multiple models) already take: the fit figures are for what is left.+ const sizeOf = (id: string) => allSizes.find(s => s.id === id);+ const keptModels = expert && multiple ? (native?.instances ?? []).filter(i => i.status !== 'error' && i.model !== selectedSize?.id) : [];+ const keptUse = keptModels.map(i => { const s = sizeOf(i.model); const card = pcGpus.find(g => g.index === i.gpus[0]); const f = s && pcRam ? fitOn(s, { ram_gb: pcRam, vram_gb: card?.vram_gb ?? pcVram }) : null; return { gpus: i.gpus, ram: f?.ramUseGb ?? 0, vram: f?.vramUseGb ?? 0 }; });+ const keptRam = keptUse.reduce((n, u) => n + u.ram, 0);+ const keptVramOn = (cards: number[]) => keptUse.filter(u => u.gpus.some(g => cards.includes(g))).reduce((n, u) => n + u.vram, 0);const loadedSelected = native?.instances.find(i => i.model === selectedSize?.id && i.status === 'ready');// A model that is already on this PC loads as it was prepared: the page shows its settings, so loading it never asks to download.useEffect(() => { if (installed?.ready) {@@ -81,6 +86,12 @@ export function NativeModels({ onOtherModels, onReady, onImport, onConnectEngineconst cardOptions = selectedSize?.gpu_options && selectedSize.gpu_options.options.length >= 2 ? selectedSize.gpu_options : null;const activeCards = cardOptions ? (cardOptions.options.find(o => o.key === cardsKey) ?? (multiple ? cardOptions.options.find(o => o.recommended && !usedBy(o.cards).length) ?? cardOptions.options.find(o => !usedBy(o.cards).length) : undefined) ?? cardOptions.options.find(o => o.recommended) ?? cardOptions.options[0]) : null;const cardsGpus: number[] = activeCards?.cards ?? [];+ const chosenCards = expert && gpus.length ? gpus : cardsGpus;+ const fitHardware = { ram_gb: pcRam ? Math.max(0, pcRam - keptRam) : pcRam, vram_gb: Math.max(0, pcVram - keptVramOn(chosenCards)) };+ // "(card 1)" in a card name is the number the screens call GPU 2 (Monitor, the model picker, the loaded list): one numbering everywhere.+ const gpuNumbers = (text: string) => text.replace(/\(card (\d+)\)/g, (_m, n) => `(GPU ${Number(n) + 1})`);+ // The fit sentence for a card choice, less what the kept models take of RAM and of that card's memory.+ const lessKept = (words: string, cards: number[]) => { const gone = Math.round(keptRam + keptVramOn(cards)); return gone > 0 ? words.replace(/of the (\d+) GB available/, (_m, n) => `of the ${Math.max(0, Number(n) - gone)} GB available`) : words; };useEffect(() => { setCardsKey(null); }, [selectedSize?.id]);const values = useMemo(() => ({ family: selectedSize?.sourceFamily, model: selectedSize?.model, context, vision: selectedSize?.images ? vision : 'no', kv, low_ram: lowRam, resourceProfile, ...(expert && gpus.length ? { gpus: gpus.join(',') } : cardsGpus.length > 1 ? { gpus: cardsGpus.join(',') } : cardsGpus.length === 1 ? { gpu: cardsGpus[0] } : {}), loadAfter: true, multiple: expert && multiple }), [selectedSize?.sourceFamily, selectedSize?.model, context, vision, kv, lowRam, resourceProfile, gpus.join(','), cardsGpus.join(','), expert, multiple]);const downloadValues = { ...values, vision: selectedSize?.images ? 'yes' : 'no', loadVision: selectedSize?.images ? vision : 'no' };@@ -147,7 +158,7 @@ export function NativeModels({ onOtherModels, onReady, onImport, onConnectEngine<div className="native-choice__col"><span className="native-choice__label">{tr("Conversation context")}</span><Select ariaLabel={tr("Conversation context")} value={String(context)} options={(native?.catalog?.contexts ?? [8192, 32768, 65536, 131072, 262144]).map(n => ({ value: String(n), label: `${n / 1024}K` }))} onChange={n => setContext(Number(n))}/></div><div className="native-choice__col"><span className="native-choice__label">{tr("Computer use")}</span><div className="native-resource-choice"><button aria-pressed={resourceProfile === 'work'} data-selected={resourceProfile === 'work'} onClick={() => setResourceProfile('work')}><Icon name="computer" size={20}/><span><strong>{tr("Leave 20% for my work")}</strong><small>{tr("Headroom for your other apps")}</small></span>{tr(resourceProfile === 'work' ? <Icon name="check" size={15}/> : null)}</button><button aria-pressed={resourceProfile === 'performance'} data-selected={resourceProfile === 'performance'} onClick={() => setResourceProfile('performance')}><Icon name="bolt" size={20}/><span><strong>{tr("Full performance")}</strong><small>{tr("Give Strata priority")}</small></span>{tr(resourceProfile === 'performance' ? <Icon name="check" size={15}/> : null)}</button></div></div></div>- {tr(cardOptions ? <div className="native-cards"><span className="native-choice__label">{tr("Graphics cards")}</span><div className="native-cards__list" role="radiogroup" aria-label={tr("Graphics cards")}>{cardOptions.options.map(o => { const on = activeCards?.key === o.key; return <button key={o.key} type="button" role="radio" aria-checked={on} data-selected={on} disabled={!!active} className="native-cards__opt" onClick={() => setCardsKey(o.key)}><span className="native-cards__dot" aria-hidden="true"/><span><strong>{o.label}</strong><small data-warn={o.verdict === 'spills' || o.verdict === 'tight' || usedBy(o.cards).length > 0}>{[o.words, ...o.notes, ...(usedBy(o.cards).length ? [tr('Already used by {0}', [usedBy(o.cards).join(', ')])] : [])].join('. ')}.</small></span></button>; })}{cardOptions.ignored.length ? <p className="small muted native-cards__note">{`Not used: ${cardOptions.ignored.map(g => `${g.name ?? 'a card'} (${g.why_ignored})`).join('; ')}.`}</p> : null}</div></div> : null)}+ {tr(cardOptions ? <div className="native-cards"><span className="native-choice__label">{tr("Graphics cards")}</span><div className="native-cards__list" role="radiogroup" aria-label={tr("Graphics cards")}>{cardOptions.options.map(o => { const on = activeCards?.key === o.key; return <button key={o.key} type="button" role="radio" aria-checked={on} data-selected={on} disabled={!!active} className="native-cards__opt" onClick={() => setCardsKey(o.key)}><span className="native-cards__dot" aria-hidden="true"/><span><strong>{gpuNumbers(o.label)}</strong><small data-warn={o.verdict === 'spills' || o.verdict === 'tight' || usedBy(o.cards).length > 0}>{[lessKept(o.words, o.cards), ...o.notes, ...(usedBy(o.cards).length ? [tr('Already used by {0}', [usedBy(o.cards).join(', ')])] : [])].join('. ')}.</small></span></button>; })}{cardOptions.ignored.length ? <p className="small muted native-cards__note">{`Not used: ${cardOptions.ignored.map(g => `${g.name ?? 'a card'} (${g.why_ignored})`).join('; ')}.`}</p> : null}</div></div> : null)}{tr(selectedSize?.imagesCapable && !selectedSize.images ? <p className="small muted native-spill-note">{tr("This model can read pictures, but the engine installed here does not include the picture reader yet, so Read pictures is off. Update the engine in Settings → About to turn it on.")}</p> : null)}{tr(selectedSize?.images ? <><div className="native-image-reading"><label><input type="checkbox" checked={vision !== 'no'} disabled={!selectedSize?.images || !!active} onChange={e => setVision(e.target.checked ? 'yes' : 'no')}/><span><strong>{tr("Read pictures ")}<small>{tr("Optional")}</small></strong><small>{tr("Understand photos, screenshots and charts. Vision files download automatically. Enable them when loading this model.")}</small></span></label>{tr(expert && vision !== 'no' ? <Select ariaLabel={tr("Image encoder device")} value={vision === 'yes' ? 'yes' : vision} options={[{ value: 'yes', label: 'Automatic' }, { value: 'gpu', label: 'GPU' }, { value: 'cpu', label: 'CPU' }]} onChange={setVision}/> : null)}</div>{tr(vision !== 'no' && installed?.ready && installed.visionPrepared === false ? <div className="native-vision-missing" role="status"><span>{tr("Picture reading needs a few more files that are not on this computer yet.")}</span><Btn size="sm" disabled={pending || !!active} onClick={() => void download()}>{tr("Download picture-reading files")}</Btn></div> : null)}</> : null)}</> : null)}@@ -160,7 +171,7 @@ export function NativeModels({ onOtherModels, onReady, onImport, onConnectEngine{tr(expert && IMAGE_GENERATION_VISIBLE ? <><details className="native-generation"><summary>{tr("Image generation ")}<span className="muted">{tr("Optional")}</span></summary><RunImageModel library={imageLibrary} disabled={pending || !!active} onChange={() => { }}/></details></> : null)}{tr(expert ? <section id="native-expert-settings" ref={expertSection} className="st-card native-execution"><h2 className="h4">{tr("Expert settings")}</h2>{tr(tunedNow ? <p className="small muted native-tuned-note">{tr("Showing the values of your tuning '{0}'.", [tunedNow.name])}</p> : null)}<label className="native-toggle"><span><strong>{tr("Run multiple models")}</strong><small>{tr("Loading another model keeps the others loaded.")}</small></span><button className="st-toggle" role="switch" aria-label={tr("Run multiple models")} aria-checked={multiple} onClick={() => setMultiple(v => !v)}/></label><h3 className="small strong">{tr("Run on")}</h3><p className="small muted">{tr("Automatic uses the installation\u2019s GPU placement. Choose a GPU, or split this model across several GPUs.")}</p><Select ariaLabel={tr("Run on")} value={deviceChoice} options={[{ value: 'auto', label: 'Automatic' }, ...(native?.hardware?.gpus ?? []).map(g => ({ value: String(g.index), label: `GPU ${g.index + 1} · ${g.name}` })), ...((native?.hardware?.gpus.length ?? 0) > 1 ? [{ value: 'split', label: 'Split across GPUs…' }] : [])]} onChange={value => { setDeviceChoice(value); setGpus(value === 'auto' ? [] : value === 'split' ? (native?.hardware?.gpus ?? []).map(g => g.index) : [Number(value)]); }}/>{tr(deviceChoice === 'split' ? <div className="native-gpu-options">{tr(native?.hardware?.gpus.map(g => <label key={g.index}><input type="checkbox" checked={gpus.includes(g.index)} onChange={e => setGpus(old => e.target.checked ? [...old, g.index] : old.filter(i => i !== g.index))}/><span>{tr("GPU ")}{tr(g.index + 1)} · {tr(g.name)}<small>{tr(g.vram_gb)}{tr(" GB VRAM")}</small></span></label>))}</div> : null)}{tr(gpus.length > 1 ? <label className="input-field"><span>{tr("Layer split")}</span><input className="st-input" value={split} placeholder={tr("auto or 16,32")} onChange={e => setSplit(e.target.value)}/></label> : null)}<div className="native-field-grid"><label className="input-field"><span>{tr("Context memory")}</span><Select ariaLabel={tr("Native KV format")} value={kv} options={[{ value: 'int8', label: 'INT8' }, { value: 'q4_0', label: 'Q4' }, { value: 'k8v4', label: 'K8 / V4' }]} onChange={setKv}/></label><label className="input-field"><span>{tr("Low-RAM mode")}</span><Select ariaLabel={tr("Native low RAM mode")} value={lowRam} options={['auto', 'resident', 'mmap'].map(v => ({ value: v, label: v === 'auto' ? 'Automatic' : v === 'resident' ? 'Keep experts in RAM' : 'Read experts from disk' }))} onChange={setLowRam}/></label></div>{tr(installed ? <><NativeSettingsFile model={installed.model}/><NativeSettings model={installed.model}/></> : <p className="small muted">{tr("More engine parameters become available after preparing this version.")}</p>)}</section> : null)}</div>- <aside className="stack stack--lg"><PcFitCard gpuName={pcGpu?.name} ramGb={pcRam} vramGb={pcVram} fit={selectedSize ? fitOn(selectedSize, fitHardware) : null}/><section className="st-card"><h2 className="h4">{tr("Model files")}</h2><p className="small muted">{tr("Strata prepares all shards, the draft layer and shared files. Completed downloads are reused.")}</p><code className="native-path">{installed?.dataFolder ?? native?.downloadDirectory ?? native?.installed?.data_folder ?? 'Choose an installation'}</code><Btn size="sm" variant="ghost" onClick={() => { setSettingsSection('Storage'); go('settings'); }}>{tr("Storage settings")}</Btn></section><Btn size="sm" variant="ghost" onClick={onOtherModels}>{tr("Other local models\u2026")}</Btn></aside>+ <aside className="stack stack--lg"><PcFitCard gpuName={pcGpu?.name} ramGb={pcRam} vramGb={pcVram} inUse={keptModels.length ? { ramGb: Math.round(keptRam), vramGb: Math.round(keptVramOn(chosenCards)) } : null} fit={selectedSize ? fitOn(selectedSize, fitHardware) : null}/><section className="st-card"><h2 className="h4">{tr("Model files")}</h2><p className="small muted">{tr("Strata prepares all shards, the draft layer and shared files. Completed downloads are reused.")}</p><code className="native-path">{installed?.dataFolder ?? native?.downloadDirectory ?? native?.installed?.data_folder ?? 'Choose an installation'}</code><Btn size="sm" variant="ghost" onClick={() => { setSettingsSection('Storage'); go('settings'); }}>{tr("Storage settings")}</Btn></section><Btn size="sm" variant="ghost" onClick={onOtherModels}>{tr("Other local models\u2026")}</Btn></aside></div><Dialog open={!!plan} title={tr(installed?.ready ? "Apply settings and load" : "Download and prepare")} compact onClose={() => !pending && setPlan(null)} actions={<><Btn disabled={pending} onClick={() => setPlan(null)}>{tr("Cancel")}</Btn><Btn variant="primary" disabled={pending || !!plan?.plan?.disk_short} onClick={() => void download()}>{tr(installed?.ready ? "Apply & load" : "Download & load")}</Btn></>}><p><strong>{tr(plan?.plan?.title ?? selectedFamily?.title)}</strong>{tr(installed?.ready ? null : <>{tr(" \u00B7 approximately ")}{tr(plan?.plan?.download_gb ?? selectedSize?.download_gb)}{tr(" GB")}</>)}</p>{tr(installed?.ready ? <p className="small muted">{tr("The model files are already on this computer. Nothing will be downloaded; only the settings you chose are applied.")}</p> : null)}{tr(plan?.plan?.disk_short ? <ErrorNotice message={plan.plan.disk_short}/> : null)}{tr(installed?.ready ? <p className="small muted">{tr("Any currently loaded native models will be unloaded first.")}</p> : <><p className="small muted">{tr("Existing files are checked and reused. Any currently loaded native models will be unloaded before preparing files.")}</p><p className="small muted">{tr("Your computer may feel slower while weights load. You can stop the download and resume later.")}</p></>)}{tr(selectedSize?.images ? <p className="small muted">{tr("Vision encoder files are included. Picture reading loads only when enabled.")}</p> : null)}</Dialog>diff --git a/apps/host/src/components/PcFitCard.tsx b/apps/host/src/components/PcFitCard.tsxindex 36726f6ac..17ca134bf 100644--- a/apps/host/src/components/PcFitCard.tsx+++ b/apps/host/src/components/PcFitCard.tsx@@ -15,12 +15,14 @@ function Meter({ label, total, use }: { label: string; total: number; use: numbe* "This computer": the graphics memory and RAM, and what the chosen version would take of each. One plain line says whether it fits* or how much would be read from the SSD (the n-gram table, which always sits on the SSD, is not counted).*/-export function PcFitCard({ gpuName, ramGb, vramGb, fit }: { gpuName?: string | null; ramGb: number | null; vramGb: number; fit: Fit | null }) {+export function PcFitCard({ gpuName, ramGb, vramGb, fit, inUse = null }: { gpuName?: string | null; ramGb: number | null; vramGb: number; fit: Fit | null; inUse?: { ramGb: number; vramGb: number } | null }) {+ const freeVram = Math.max(0, vramGb - (inUse?.vramGb ?? 0)), freeRam = ramGb ? Math.max(0, ramGb - (inUse?.ramGb ?? 0)) : 0;return <section className="st-card pc-card"><div><h2 className="h4">{tr("This computer")}</h2><p className="small muted">{tr(gpuName ? tr("{0} · {1} graphics memory", [gpuName, gb(vramGb)]) : tr("No supported graphics card reported by this installation."))}{ramGb ? tr(" · {0} RAM", [gb(ramGb)]) : ''}</p></div>- {tr(fit?.known && vramGb > 0 ? <Meter label="Graphics memory" total={vramGb} use={fit.vramUseGb}/> : null)}- {tr(fit?.known && ramGb ? <Meter label="RAM" total={ramGb} use={fit.ramUseGb}/> : null)}+ {tr(fit?.known && vramGb > 0 ? <Meter label="Graphics memory" total={freeVram} use={fit.vramUseGb}/> : null)}+ {tr(fit?.known && ramGb ? <Meter label="RAM" total={freeRam} use={fit.ramUseGb}/> : null)}+ {tr(inUse ? <p className="xs muted">{tr("Models that stay loaded use about {0} GB of RAM and {1} GB of this card’s memory.", [inUse.ramGb, inUse.vramGb])}</p> : null)}{tr(fit?.known ? <p className="pc-note">{tr(fit.spillGb >= 1 ? 'About {0} GB will be read from the SSD, so answers can be a little slower.' : 'Fits fully in memory.', [Math.round(fit.spillGb)])}</p> : null)}</section>;}diff --git a/apps/host/src/lib/runtime-models.ts b/apps/host/src/lib/runtime-models.tsindex 0b2722510..b974cd29c 100644--- a/apps/host/src/lib/runtime-models.ts+++ b/apps/host/src/lib/runtime-models.ts@@ -26,4 +26,4 @@ export function scopedMonitor(live:MonitorState|null,runtime:RuntimeModels|null,totals:{...live.totals,tokensIn:count('tokensIn'),tokensOut:count('tokensOut'),requests:done.length,cachedTokens:0,uncachedTokens:count('tokensIn'),promptMs:undefined,decodeMs:undefined,avgTps:0}};}-export const instanceLabel=(i:RuntimeModel)=>`${i.family} · ${i.name}${i.memory.context>0?` · ${i.memory.context/1024}K`:""}`;+export const instanceLabel=(i:RuntimeModel)=>`${i.family}${i.family.toLowerCase().endsWith(i.name.toLowerCase())?"":` · ${i.name}`}${i.memory.context>0?` · ${i.memory.context/1024}K`:""}`;diff --git a/apps/host/src/locales/de.json b/apps/host/src/locales/de.jsonindex 488056543..942a2f11e 100644--- a/apps/host/src/locales/de.json+++ b/apps/host/src/locales/de.json@@ -3197,5 +3197,6 @@"s3201": "cloudflared läuft bereits für andere Tunnel (PIDs {0}).","s3202": "Der Strata-Tunnel für diese Adresse läuft bereits (PID {0}).","s3203": "Der Strata-Tunnel für diese Adresse läuft bereits.",- "s3204": "Beende ihn zuerst oder nutze ihn, wie er ist, und verbinde dich dann hier erneut."+ "s3204": "Beende ihn zuerst oder nutze ihn, wie er ist, und verbinde dich dann hier erneut.",+ "s3205": "Modelle, die geladen bleiben, belegen etwa {0} GB RAM und {1} GB des Speichers dieser Karte."}diff --git a/apps/host/src/locales/en.json b/apps/host/src/locales/en.jsonindex 213db3c79..55daabe68 100644--- a/apps/host/src/locales/en.json+++ b/apps/host/src/locales/en.json@@ -3197,5 +3197,6 @@"s3201": "cloudflared is already running for other tunnels (PIDs {0}).","s3202": "Strata’s tunnel for this address is already running (PID {0}).","s3203": "Strata’s tunnel for this address is already running.",- "s3204": "Stop it first, or use it as it is, then connect again here."+ "s3204": "Stop it first, or use it as it is, then connect again here.",+ "s3205": "Models that stay loaded use about {0} GB of RAM and {1} GB of this card’s memory."}diff --git a/apps/host/src/locales/es.json b/apps/host/src/locales/es.jsonindex ec551558e..a9a02d192 100644--- a/apps/host/src/locales/es.json+++ b/apps/host/src/locales/es.json@@ -3197,5 +3197,6 @@"s3201": "cloudflared ya se está ejecutando para otros túneles (PID {0}).","s3202": "El túnel de Strata para esta dirección ya se está ejecutando (PID {0}).","s3203": "El túnel de Strata para esta dirección ya se está ejecutando.",- "s3204": "Deténlo primero, o úsalo tal como está, y vuelve a conectar aquí."+ "s3204": "Deténlo primero, o úsalo tal como está, y vuelve a conectar aquí.",+ "s3205": "Los modelos que siguen cargados usan unos {0} GB de RAM y {1} GB de la memoria de esta tarjeta."}diff --git a/apps/host/src/locales/ja.json b/apps/host/src/locales/ja.jsonindex 4373f3dfe..d13d0775c 100644--- a/apps/host/src/locales/ja.json+++ b/apps/host/src/locales/ja.json@@ -3197,5 +3197,6 @@"s3201": "cloudflared は他のトンネル用にすでに動作しています(PID {0})。","s3202": "このアドレス用のStrataのトンネルはすでに動作しています(PID {0})。","s3203": "このアドレス用のStrataのトンネルはすでに動作しています。",- "s3204": "先にそれを停止するか、そのまま使ってから、ここで再度接続してください。"+ "s3204": "先にそれを停止するか、そのまま使ってから、ここで再度接続してください。",+ "s3205": "読み込んだままのモデルが、RAMを約 {0} GB、このカードのメモリを約 {1} GB 使用します。"}diff --git a/apps/host/src/locales/ko.json b/apps/host/src/locales/ko.jsonindex 206d11c08..840e32384 100644--- a/apps/host/src/locales/ko.json+++ b/apps/host/src/locales/ko.json@@ -3197,5 +3197,6 @@"s3201": "cloudflared가 이미 다른 터널용으로 실행 중입니다(PID {0}).","s3202": "이 주소용 Strata 터널이 이미 실행 중입니다(PID {0}).","s3203": "이 주소용 Strata 터널이 이미 실행 중입니다.",- "s3204": "먼저 중지하거나 그대로 사용한 뒤 여기서 다시 연결하세요."+ "s3204": "먼저 중지하거나 그대로 사용한 뒤 여기서 다시 연결하세요.",+ "s3205": "계속 불러 둔 모델이 RAM 약 {0} GB와 이 카드 메모리 약 {1} GB를 사용합니다."}diff --git a/apps/host/src/locales/pt.json b/apps/host/src/locales/pt.jsonindex cf10edee4..824e2b3d0 100644--- a/apps/host/src/locales/pt.json+++ b/apps/host/src/locales/pt.json@@ -3197,5 +3197,6 @@"s3201": "O cloudflared já está em execução para outros túneis (PIDs {0}).","s3202": "O túnel do Strata para este endereço já está em execução (PID {0}).","s3203": "O túnel do Strata para este endereço já está em execução.",- "s3204": "Pare-o primeiro, ou use-o como está, e conecte novamente aqui."+ "s3204": "Pare-o primeiro, ou use-o como está, e conecte novamente aqui.",+ "s3205": "Os modelos que continuam carregados usam cerca de {0} GB de RAM e {1} GB da memória desta placa."}diff --git a/apps/host/src/locales/ru.json b/apps/host/src/locales/ru.jsonindex 194ff4cd0..6b7b6e5cd 100644--- a/apps/host/src/locales/ru.json+++ b/apps/host/src/locales/ru.json@@ -3197,5 +3197,6 @@"s3201": "cloudflared уже запущен для других туннелей (PID {0}).","s3202": "Туннель Strata для этого адреса уже запущен (PID {0}).","s3203": "Туннель Strata для этого адреса уже запущен.",- "s3204": "Сначала остановите его или используйте как есть, затем подключитесь здесь снова."+ "s3204": "Сначала остановите его или используйте как есть, затем подключитесь здесь снова.",+ "s3205": "Модели, которые остаются загруженными, занимают около {0} ГБ ОЗУ и {1} ГБ памяти этой карты."}diff --git a/apps/host/src/locales/zh.json b/apps/host/src/locales/zh.jsonindex 86ef6fa18..4712f79c9 100644--- a/apps/host/src/locales/zh.json+++ b/apps/host/src/locales/zh.json@@ -3197,5 +3197,6 @@"s3201": "cloudflared 已在为其他隧道运行(PID {0})。","s3202": "这个地址的 Strata 隧道已在运行(PID {0})。","s3203": "这个地址的 Strata 隧道已在运行。",- "s3204": "请先停止它,或直接使用它,然后在这里重新连接。"+ "s3204": "请先停止它,或直接使用它,然后在这里重新连接。",+ "s3205": "保持加载的模型大约占用 {0} GB 内存和这块显卡 {1} GB 的显存。"}diff --git a/apps/host/tests/native-two-models.test.mjs b/apps/host/tests/native-two-models.test.mjsindex cca9f6cca..1f3f8c8da 100644--- a/apps/host/tests/native-two-models.test.mjs+++ b/apps/host/tests/native-two-models.test.mjs@@ -35,3 +35,35 @@ test('a model that failed to start is not offered in the chat model picker', asyconst picker = await readFile(new URL('../src/components/ChatModelPicker.tsx', import.meta.url), 'utf8');assert.equal((picker.match(/native\?\.instances\.filter\(i => i\.status !== 'error'\)\.map/g) ?? []).length, 2);});++import { friendlyModelName } from '../server/model-names.mjs';+test('a loaded model is named from the catalog (family and version), the file id only as a fallback', async () => {+ const catalog = { families: [{ title: 'Qwen3.8-Flash-Next', sizes: [{ id: 'q2_0', model: 'Q2_0' }] }, { title: 'Qwen3.8-Flash-Next (Gyro)', sizes: [{ id: 'gyro-gyro-s', model: 'Gyro-S' }] }] };+ assert.equal(friendlyModelName(catalog, 'q2_0'), 'Qwen3.8-Flash-Next Q2_0');+ assert.equal(friendlyModelName(catalog, 'gyro-gyro-s'), 'Qwen3.8-Flash-Next Gyro-S');+ assert.equal(friendlyModelName(catalog, 'nope'), null);+ assert.equal(friendlyModelName(null, 'q2_0'), null);+ const f = nativeFixture();+ try {+ await f.control.refresh(true);+ const done = await finishJob(f.control, f.control.operation('load', { model: 'iq2_xs' }).id);+ assert.equal(done.state, 'done', done.error);+ assert.equal(f.control.state().instances[0].label, 'Qwen3.8-Flash-Next IQ2_XS');+ } finally { await f.cleanup(); }+});++test('card names use the GPU numbering of the other screens, and the fit figures subtract the models that stay loaded', async () => {+ const models = await readFile(new URL('../src/components/NativeModels.tsx', import.meta.url), 'utf8');+ assert.ok(models.includes('(GPU ${Number(n) + 1})') && models.includes('text.replace(/\\(card (\\d+)\\)/g'));+ assert.match(models, /<strong>\{gpuNumbers\(o\.label\)\}<\/strong>/);+ assert.match(models, /const keptModels = expert && multiple/);+ assert.match(models, /inUse=\{keptModels\.length \?/);+ const card = await readFile(new URL('../src/components/PcFitCard.tsx', import.meta.url), 'utf8');+ assert.match(card, /total=\{freeVram\}/);+ assert.match(card, /total=\{freeRam\}/);+ // the arithmetic itself+ const text = 'fits: needs 44 GB of the 273 GB available.';+ const gone = Math.round(14 + 27);+ assert.equal(text.replace(/of the (\d+) GB available/, (_m, n) => `of the ${Math.max(0, Number(n) - gone)} GB available`), 'fits: needs 44 GB of the 232 GB available.');+ assert.equal('RX 9070 (card 0) + RAM'.replace(/\(card (\d+)\)/g, (_m, n) => `(GPU ${Number(n) + 1})`), 'RX 9070 (GPU 1) + RAM');+});