src/app/features/settings/general/General.tsx

@@ -2037,7 +2037,7 @@ export function Calls() {
                 <Text size="L400">Model</Text>
                 <SettingTile
                   title="ML model"
-                  description="Choose the machine learning model used for noise removal. Heavier models clean more aggressively at a higher CPU cost."
+                  description="Choose the machine learning model used for noise removal. Heavier models clean more aggressively at a higher CPU cost. CPU figures are the share of one processor core during a call on a mid-range desktop; Task Manager shows that divided by your number of cores, and slower computers use more."
                   after={
                     <SettingsSelect<DenoiseModelId>
                       value={callDenoiseModel}
@@ -2064,7 +2064,7 @@ export function Calls() {
                     <Box direction="Row" gap="400" wrap="Wrap">
                       {(
                         [
-                          { label: 'CPU', value: selectedDenoiseModel.cpuUsage },
+                          { label: 'CPU (one core)', value: selectedDenoiseModel.cpuUsage },
                           { label: 'Voice quality', value: selectedDenoiseModel.voiceQuality },
                           { label: 'Transients', value: selectedDenoiseModel.transients },
                           { label: 'Download', value: selectedDenoiseModel.binarySize },

src/app/utils/lotusDenoiseUtils.ts

@@ -7,6 +7,9 @@
 
 import { DenoiseModelId } from '../state/settings';
 
+// CPU = share of ONE core while in a call, measured with each model running
+// exactly as Lotus Call runs it (Ryzen 7 PRO 4750GE, Chromium); download = bytes
+// actually fetched on first use. Re-measure when a model or its settings change.
 export type DenoiseModel = {
   id: DenoiseModelId;
   name: string;
@@ -24,7 +27,7 @@ export const DENOISE_MODELS: DenoiseModel[] = [
     name: 'DeepFilterNet 3 (beta)',
     description:
       'Studio-grade deep-learning model (48 kHz fullband, ONNX). Best quality; highest CPU and a larger one-time download.',
-    cpuUsage: '25-50%',
+    cpuUsage: '~30%',
     binarySize: '~18 MB',
     transients: 'Excellent',
     voiceQuality: 'Very High',
@@ -34,8 +37,8 @@ export const DENOISE_MODELS: DenoiseModel[] = [
     name: 'DTLN (beta)',
     description:
       'Dual-signal deep-learning model (16 kHz). Strong on transient noise; moderate CPU.',
-    cpuUsage: '10-20%',
-    binarySize: '~4 MB',
+    cpuUsage: '~9%',
+    binarySize: '~20 MB',
     transients: 'Excellent',
     voiceQuality: 'High',
   },
@@ -44,7 +47,7 @@ export const DENOISE_MODELS: DenoiseModel[] = [
     name: 'RNNoise',
     description:
       'Lightweight hybrid model (48 kHz). Very low CPU; good for steady noise like fans, but can sound processed at full strength.',
-    cpuUsage: '< 5%',
+    cpuUsage: '~3%',
     binarySize: '< 1 MB',
     transients: 'Good',
     voiceQuality: 'Moderate',
@@ -54,7 +57,7 @@ export const DENOISE_MODELS: DenoiseModel[] = [
     name: 'Speex (Legacy)',
     description:
       'Classic DSP noise suppressor. Minimal CPU, gentlest on voice; weakest suppression.',
-    cpuUsage: '< 2%',
+    cpuUsage: '~2%',
     binarySize: '< 1 MB',
     transients: 'Poor',
     voiceQuality: 'Moderate',