adjust staus panel

static/script.js

@@ -181,15 +181,24 @@ function updateRunningModels(models) {
         return;
     }
     
-    container.innerHTML = models.map(model => `
+    container.innerHTML = models.map(model => {
+        const gpuLayers = model.gpu_layers || 0;
+        const totalLayers = model.total_layers || 0;
+        const cpuLayers = totalLayers > 0 ? totalLayers - gpuLayers : 0;
+        
+        return `
         <div class="running-model">
             <div class="running-model-name">${escapeHtml(model.name)}</div>
             <div class="running-model-stats">
                 VRAM: ${model.vram_gb.toFixed(2)} GB
                 ${model.offload_pct > 0 ? ` | CPU: ${model.offload_pct.toFixed(1)}%` : ''}
             </div>
+            <div class="running-model-layers">
+                GPU: ${gpuLayers} layers | CPU: ${cpuLayers} layers
+            </div>
         </div>
-    `).join('');
+        `;
+    }).join('');
 }
 
 // ===== MODEL MANAGEMENT =====

static/style.css

@@ -110,8 +110,16 @@ body {
 }
 
 .running-model-stats {
-    font-size: 11px;
+    font-size: 0.85rem;
     color: var(--text-secondary);
+    margin-top: 0.25rem;
+}
+
+.running-model-layers {
+    font-size: 0.85rem;
+    color: var(--accent);
+    margin-top: 0.25rem;
+    font-weight: 500;
 }
 
 .no-models {

web_app.py

@@ -398,12 +398,19 @@ def api_status():
                 size_total = model.get('size', 0) / (1024**3)  # GB
                 offload_pct = ((size_total - size_vram) / size_total * 100) if size_total > 0 else 0
                 
+                # Extract layer information from model details
+                details = model.get('details', {})
+                total_layers = details.get('parameter_size', 0)
+                gpu_layers = details.get('quantization_level', 0)
+                
                 running_models.append({
                     'name': model.get('name', 'Unknown'),
                     'size_gb': size_total,
                     'vram_gb': size_vram,
                     'offload_pct': offload_pct,
-                    'expires_at': model.get('expires_at', '')
+                    'expires_at': model.get('expires_at', ''),
+                    'gpu_layers': gpu_layers,
+                    'total_layers': total_layers
                 })
     except Exception as e:
         print(f"Error getting running models: {e}")