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++
import type { GpuInfo, GpuReading } from './types';
export const hasReading=(v:unknown):v is number=>typeof v==='number'&&Number.isFinite(v);
export const gpuId=(gpu:GpuInfo)=>gpu.id??`${gpu.vendor}:${gpu.index}`;
/** A total, mean, or maximum must cover every selected device. Partial totals are misleading. */
export function gpuMetric(devices:GpuInfo[],readings:GpuReading[]|undefined,key:keyof GpuReading,mode:'sum'|'mean'|'max'='sum'):number|null {
const values=devices.map(device=>readings?.find(reading=>reading.id===gpuId(device))?.[key]);
if(!values.length||!values.every(hasReading))return null;
if(key==='memoryUsedGb'&&mode==='sum') {
const shared=values.filter((_,i)=>devices[i].unified),dedicated=values.filter((_,i)=>!devices[i].unified);
return dedicated.reduce((n,v)=>n+v,0)+(shared.length?Math.max(...shared):0);
}
return mode==='max'?Math.max(...values):values.reduce((n,v)=>n+v,0)/(mode==='mean'?values.length:1);
}
/** The card's name without its maker: "NVIDIA GeForce RTX 5070" -> "RTX 5070". */
export const shortGpuName=(name:string)=>String(name??'').replace(/^(NVIDIA|AMD|Intel)(\(R\)|\(TM\))?\s+/i,'').replace(/^(GeForce|Radeon|Arc)(\(TM\))?\s+/i,'').trim()||String(name??'');
/**
* The reading over the cards that DO report this value. A card that cannot report it (an integrated one without a temperature sensor) is left
* out instead of blanking the figure; `partial` says some were left out, and `devices` names the cards the figure is from.
*/
export function gpuReported(devices:GpuInfo[],readings:GpuReading[]|undefined,key:keyof GpuReading,mode:'sum'|'mean'|'max'='sum'):{value:number|null;devices:GpuInfo[];partial:boolean} {
const reporting=devices.filter(device=>hasReading(readings?.find(reading=>reading.id===gpuId(device))?.[key]));
return {value:reporting.length?gpuMetric(reporting,readings,key,mode):null,devices:reporting,partial:reporting.length>0&&reporting.length<devices.length};
}
export function gpuCapacity(devices:GpuInfo[]) {
const shared=devices.filter(g=>g.unified).map(g=>g.vramGb);
return devices.filter(g=>!g.unified).reduce((n,g)=>n+g.vramGb,0)+(shared.length?Math.max(...shared):0);
}
/**
* The cards "All GPUs" covers by default. A small integrated chip (an AMD or Intel adapter on the Windows/Vulkan list with a carve-out under
* 2 GB) beside a real card is left out: Strata cannot run a model on it (the native engine report marks it unusable), and counting it adds a
* second "GPU" and half a gigabyte to every total. It stays in the picker. Alone (a Strix Halo, an iGPU-only PC) it stays the default.
*/
export function defaultGpuSet(devices:GpuInfo[]):GpuInfo[] {
const real=(g:GpuInfo)=>g.vramGb>=4||g.vendor==='nvidia'||g.backend==='cuda';
const small=(g:GpuInfo)=>g.backend==='vulkan'&&(g.vendor==='amd'||g.vendor==='intel')&&g.vramGb<2&&!g.unified;
if(!devices.some(real))return devices;
const kept=devices.filter(g=>!small(g));
return kept.length?kept:devices;
}