diff --git a/src/config/models/mlc-models.json b/src/config/models/mlc-models.json
index 6efa090..3d66c4f 100644
--- a/src/config/models/mlc-models.json
+++ b/src/config/models/mlc-models.json
@@ -1,4 +1,27 @@
 {
+    "gemma-3-1b-it": {
+        "engine": "mlc",
+        "modelName": "Gemma-3-1B-Instruct",
+        "modelType": "text-generation",
+        "repo": "mlc-ai/gemma-3-1b-it-{quantization}-MLC",
+        "quantizations": [
+            "q4f16_1",
+            "q4f32_1"
+        ],
+        "defaultQuantization": "q4f32_1",
+        "defaultParams": {
+            "temperature": 0.7,
+            "maxTokens": 2048
+        },
+        "pipeline": "text-generation",
+        "required_features": [
+            "shader-f16"
+        ],
+        "metadata": {
+            "context_window_size": 32768,
+            "description": "Google Gemma 3 1B Instruct — smallest Gemma variant, fits in ~1 GB VRAM"
+        }
+    },
     "llama-3.2-1b-instruct": {
         "engine": "mlc",
         "modelName": "Llama-3.2-1B-Instruct",
diff --git a/src/core/agent/html-cleaner.ts b/src/core/agent/html-cleaner.ts
index af95d5d..842e618 100644
--- a/src/core/agent/html-cleaner.ts
+++ b/src/core/agent/html-cleaner.ts
@@ -41,6 +41,62 @@ export class HTMLCleaner {
     return doc.body;
   }
 
+  /**
+   * Removes elements that are explicitly hidden or are responsive-design duplicates.
+   *
+   * Many sites include the same content twice — once for mobile and once for desktop —
+   * controlling visibility via CSS classes or inline styles. Since DOMParser runs without
+   * stylesheets we cannot resolve class-based visibility, but we can prune elements that
+   * use explicit DOM signals to indicate they are non-primary content:
+   *
+   * 1. `aria-hidden="true"` — explicitly hidden from assistive technologies; almost always
+   *    a decorative duplicate (e.g. a mobile nav icon that mirrors visible text).
+   * 2. `style="display:none"` / `style="visibility:hidden"` — inline-hidden elements that
+   *    are never visible regardless of which CSS is loaded.
+   * 3. CSS class names containing "mobile", "desktop", "tablet" combined with common
+   *    hide/show utility words ("hidden", "only", "show", "hide", "visible") — a heuristic
+   *    that catches Tailwind / Bootstrap / custom responsive utilities.
+   *
+   * @private
+   * @param {HTMLElement} root - The parsed DOM element to prune in-place
+   */
+  private removeHiddenAndDuplicateElements(root: HTMLElement): void {
+    // Responsive class patterns that signal show/hide intent.
+    // Match e.g. "mobile-only", "desktop-hidden", "show-on-tablet", "hidden-xs"
+    const RESPONSIVE_PATTERN =
+      /\b(mobile|desktop|tablet|phone|sm|md|lg|xl)\b.{0,10}\b(only|hidden|hide|show|visible|invisible)\b|\b(hidden|hide|show|visible|invisible)\b.{0,10}\b(mobile|desktop|tablet|phone|sm|md|lg|xl)\b/i;
+
+    const toRemove: Element[] = [];
+
+    root.querySelectorAll('*').forEach((el) => {
+      // 1. aria-hidden="true"
+      if (el.getAttribute('aria-hidden') === 'true') {
+        toRemove.push(el);
+        return;
+      }
+
+      // 2. Inline display:none or visibility:hidden
+      const style = (el as HTMLElement).style;
+      if (style) {
+        if (style.display === 'none' || style.visibility === 'hidden') {
+          toRemove.push(el);
+          return;
+        }
+      }
+
+      // 3. Responsive class heuristic
+      const className = el.className;
+      if (typeof className === 'string' && RESPONSIVE_PATTERN.test(className)) {
+        toRemove.push(el);
+      }
+    });
+
+    // Remove in reverse document order so parent removal doesn't invalidate children
+    for (let i = toRemove.length - 1; i >= 0; i--) {
+      toRemove[i].remove();
+    }
+  }
+
   /**
    * Cleans HTML content by removing specified tags and attributes, returning only text content.
    * @param {string} html - The HTML content to clean
@@ -49,6 +105,9 @@ export class HTMLCleaner {
   clean(html: string): string {
     const tempElement = this.parseHTML(html);
 
+    // Remove hidden elements and responsive-design duplicates before extracting text
+    this.removeHiddenAndDuplicateElements(tempElement);
+
     this.tagsToRemove.forEach((tag) => {
       let elements = tempElement.querySelectorAll(tag);
       elements.forEach((el) => el.remove());
@@ -71,6 +130,7 @@ export class HTMLCleaner {
    */
   cleanSemantic(html: string): string {
     const tempElement = this.parseHTML(html);
+    this.removeHiddenAndDuplicateElements(tempElement);
     let importantText = '';
     const importantTags = [
       'article',
@@ -141,6 +201,7 @@ export class HTMLCleaner {
    */
   preserveSemanticHierarchy(html: string): string {
     const tempElement = this.parseHTML(html);
+    this.removeHiddenAndDuplicateElements(tempElement);
 
     const headingLevels = ['h1', 'h2', 'h3', 'h4', 'h5', 'h6'];
     let structuredContent = '';
diff --git a/src/engines/transformer-engine-wrapper.ts b/src/engines/transformer-engine-wrapper.ts
index c60f80e..39be468 100644
--- a/src/engines/transformer-engine-wrapper.ts
+++ b/src/engines/transformer-engine-wrapper.ts
@@ -13,6 +13,22 @@ import { ModelConfig } from '../config/models/types';
 import { TTSEngine, SAMPLE_RATE as TTS_SAMPLE_RATE } from './tts-engine';
 import { AutoProcessor, MultiModalityCausalLM } from '../libs/transformers/transformers';
 
+/**
+ * Detect whether a usable WebGPU adapter is available.
+ * Falls back to CPU (ONNX WASM backend) when WebGPU is absent or fails.
+ */
+async function detectBestDevice(): Promise<'webgpu' | 'cpu'> {
+  if (typeof navigator === 'undefined' || !('gpu' in navigator)) return 'cpu';
+  try {
+    const adapter = await (
+      navigator as unknown as { gpu: { requestAdapter(): Promise<unknown> } }
+    ).gpu.requestAdapter();
+    return adapter ? 'webgpu' : 'cpu';
+  } catch {
+    return 'cpu';
+  }
+}
+
 export class TransformersEngineWrapper {
   private transformersPipeline:
     | TextGenerationPipeline
@@ -48,7 +64,15 @@ export class TransformersEngineWrapper {
 
       this.modelType = modelConfig.modelType;
 
-      options.device = 'webgpu';
+      // Detect the best available compute device; fall back to CPU/WASM when
+      // WebGPU is unavailable (e.g. Firefox, older Chromium, Node.js).
+      // Callers may still override by passing `options.device` explicitly.
+      if (!options.device) {
+        options.device = await detectBestDevice();
+        if (options.device === 'cpu') {
+          console.info('[Transformers] WebGPU unavailable — falling back to CPU/WASM inference');
+        }
+      }
 
       // Configure pipeline options with proper worker settings
       const pipelineOptions = {
@@ -67,7 +91,6 @@ export class TransformersEngineWrapper {
 
       // Initialize image processor for multimodal models
       if (modelConfig.modelType === 'multimodal') {
-        options.device = 'webgpu';
         // console.log('Loading multimodal model...');
         this.imageProcessor = await AutoProcessor.from_pretrained(modelConfig.repo, pipelineOptions);
         // console.log('Image processor loaded');