diff --git a/build/output/start-llama-server.bat b/build/output/start-llama-server.bat
index 51f8984..f008a50 100644
--- a/build/output/start-llama-server.bat
+++ b/build/output/start-llama-server.bat
@@ -1,125 +1,244 @@
 @echo off
+
+title Hermes Portable - Offline LLM Server with GPU Detection
+
 :: ==============================================================================
-:: Hermes Portable Rescue - llama-server launcher with GPU detection
+
+:: Hermes Portable Rescue - llama-server launcher with multi-brand GPU detection
+
 :: ==============================================================================
+
 :: Detects GPU brand (NVIDIA, AMD, Intel, integrated) and launches the
+
 :: appropriate llama-server build (Vulkan for GPU, CPU-only fallback).
+
 :: ==============================================================================
+
 setlocal enabledelayedexpansion
 
+
+
 cd /d "%~dp0"
 
-set LLAMA_DIR=%~dp0bin\llama
-set MODEL_DIR=%~dp0bin\ollama
-set MODEL=%MODEL_DIR%\qwen2.5-coder-1.5b-q4_k_m.gguf
+
+
+set LLAMA_DIR=%~dp0bin\ollama
+
+set MODEL=%LLAMA_DIR%\Llama-3.2-1B-Instruct-Q4_K_M.gguf
+
 set PORT=11434
+
 set GPU_FOUND=0
 
+
+
 echo.
+
 echo ============================================
+
 echo   Hermes LLM Server - GPU Detection
+
 echo ============================================
+
 echo.
 
+
+
 :: --- Detection 1: nvidia-smi (NVIDIA) --------------------------------------
+
 nvidia-smi >nul 2>&1
+
 if !errorlevel! equ 0 (
+
     for /f "tokens=*" %%a in ('nvidia-smi --query-gpu=name --format=csv,noheader 2^>nul') do (
+
         set GPU_NAME=%%a
+
     )
+
     echo [OK] NVIDIA GPU detected: !GPU_NAME!
+
     set GPU_FOUND=1
+
 )
 
-::  Detection 2: WMIC - check for AMD/Intel GPUs 
+
+
+:: --- Detection 2: WMIC - check for AMD/Intel GPUs ---------------------------
+
 if !GPU_FOUND! equ 0 (
+
     wmic path win32_videocontroller get name 2>nul | findstr /i "nvidia" >nul
+
     if !errorlevel! equ 0 (
+
         echo [OK] NVIDIA GPU detected via WMI
+
         set GPU_FOUND=1
+
     ) else (
+
         wmic path win32_videocontroller get name 2>nul | findstr /i "amd radeon" >nul
+
         if !errorlevel! equ 0 (
+
             echo [OK] AMD GPU detected via WMI
+
             set GPU_FOUND=1
+
         ) else (
+
             wmic path win32_videocontroller get name 2>nul | findstr /i "intel arc" >nul
+
             if !errorlevel! equ 0 (
+
                 echo [OK] Intel GPU detected via WMI
+
                 set GPU_FOUND=1
+
             ) else (
+
                 wmic path win32_videocontroller get name 2>nul | findstr /i "intel hd intel iris intel uhd" >nul
+
                 if !errorlevel! equ 0 (
+
                     echo [OK] Intel integrated graphics detected via WMI
+
                     set GPU_FOUND=1
+
                 )
+
             )
+
         )
+
     )
+
 )
 
-::  Detection 3: vulkaninfo (direct Vulkan probe) 
+
+
+:: --- Detection 3: vulkaninfo (direct Vulkan probe) ---------------------------
+
 if !GPU_FOUND! equ 0 (
+
     where vulkaninfo >nul 2>&1
+
     if !errorlevel! equ 0 (
+
         vulkaninfo --summary 2>nul | findstr /c:"Vulkan Instance" >nul
+
         if !errorlevel! equ 0 (
+
             echo [OK] Vulkan-capable device detected
+
             set GPU_FOUND=1
+
         )
+
     )
+
 )
 
-::  Check model exists 
+
+
+:: --- Check model exists ----------------------------------------------------
+
 if not exist "!MODEL!" (
+
     echo [ERROR] Model not found: !MODEL!
+
     echo.
+
     echo Please download a GGUF model and place it at:
+
     echo   !MODEL!
+
     echo.
-    echo Recommended: Qwen 2.5 Coder 1.5B Q4_K_M
-    echo   https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct-GGUF
-    echo.
+
     pause
+
     exit /b 1
+
 )
 
-::  Launch 
+
+
+:: --- Launch ----------------------------------------------------------------
+
 if !GPU_FOUND! equ 1 (
+
     echo.
+
     echo [*] Starting llama-server with GPU acceleration (Vulkan)...
-    echo [*] Model: qwen2.5-coder-1.5b-q4_k_m.gguf
+
+    echo [*] Model: Llama-3.2-1B (Q4_K_M)
+
     echo [*] Server: http://127.0.0.1:!PORT!/v1
+
     echo [*] Flags: --n-gpu-layers 99 --mlock --cont-batching -c 4096
+
     echo.
+
     echo [*] Press Ctrl+C to stop the server.
+
     echo.
 
+
+
+    "!LLAMA_DIR!\llama-server-vulkan.exe" ^
+
+        --host 127.0.0.1 --port !PORT! ^
+
+        -m "!MODEL!" ^
+
+        --n-gpu-layers 99 ^
+
+        --mlock ^
+
+        --cont-batching ^
+
+        -c 4096
+
+) else (
+
+    echo.
+
+    echo [*] No compatible GPU found. Starting CPU-only mode.
+
+    echo [*] Model: Llama-3.2-1B (Q4_K_M)
+
+    echo [*] Server: http://127.0.0.1:!PORT!/v1
+
+    echo [*] Flags: --mlock --cont-batching -c 4096
+
+    echo.
+
+    echo [*] Press Ctrl+C to stop the server.
+
+    echo.
+
+
+
     "!LLAMA_DIR!\llama-server.exe" ^
-        --host 127.0.0.1 --port !PORT! ^
-        -m "!MODEL!" ^
-        --n-gpu-layers 99 ^
-        --mlock ^
-        --cont-batching ^
-        -c 4096
-) else (
-    echo.
-    echo [*] No compatible GPU found. Starting CPU-only mode.
-    echo [*] Model: qwen2.5-coder-1.5b-q4_k_m.gguf
-    echo [*] Server: http://127.0.0.1:!PORT!/v1
-    echo [*] Flags: --mlock --cont-batching -c 4096
-    echo.
-    echo [*] Press Ctrl+C to stop the server.
-    echo.
 
-    "!LLAMA_DIR!\cpu\llama-server-cpu.exe" ^
         --host 127.0.0.1 --port !PORT! ^
+
         -m "!MODEL!" ^
+
         --mlock ^
+
         --cont-batching ^
+
         -c 4096
+
 )
 
+
+
 echo.
+
 echo [*] Server exited with code !errorlevel!
+
 pause
+
diff --git a/build/quick-rebuild-iso.sh b/build/quick-rebuild-iso.sh
index fcf39ae..b8953f0 100755
--- a/build/quick-rebuild-iso.sh
+++ b/build/quick-rebuild-iso.sh
@@ -7,7 +7,7 @@ PROJECT_DIR="$(cd "$SCRIPT_DIR/.." && pwd)"
 BUILD_DIR="$PROJECT_DIR/build"
 EXISTING_ISO="$BUILD_DIR/output/hermes-rescue.iso"
 OUTPUT_DIR="$BUILD_DIR/output"
-WORKDIR="/tmp/hermes-iso-quick"
+WORKDIR="${WORKDIR:-/tmp/hermes-iso-quick}"
 SOURCE_DIR="$PROJECT_DIR/src"
 
 info()  { echo -e "\033[0;34m[INFO]\033[0m  $*"; }
@@ -21,7 +21,8 @@ done
 
 [[ -f "$EXISTING_ISO" ]] || die "Existing ISO not found: $EXISTING_ISO"
 
-rm -rf "$WORKDIR"
+# Clean workdir contents (handles bind mounts safely)
+rm -rf "$WORKDIR" 2>/dev/null || (rm -rf "$WORKDIR"/* 2>/dev/null; true)
 mkdir -p "$WORKDIR/iso-contents" "$WORKDIR/squashfs-root"
 
 info "Mounting existing ISO..."
@@ -40,15 +41,15 @@ unsquashfs -d "$WORKDIR/squashfs-root" -f "$WORKDIR/filesystem.squashfs" 2>&1 |
 ok "Squashfs extracted ($(du -sh "$WORKDIR/squashfs-root" | cut -f1))"
 
 info "Updating config.yaml..."
-cp "$SOURCE_DIR/hermes/config.yaml" "$WORKDIR/squashfs-root/hermes/config.yaml"
+cp "$SOURCE_DIR/hermes/config.yaml" "$WORKDIR/squashfs-root/opt/hermes/config.yaml"
 ok "config.yaml updated"
 
 info "Updating auth.json..."
-cp "$SOURCE_DIR/hermes/auth.json" "$WORKDIR/squashfs-root/hermes/auth.json"
+cp "$SOURCE_DIR/hermes/auth.json" "$WORKDIR/squashfs-root/opt/hermes/auth.json"
 ok "auth.json updated"
 
 info "Updating autorun.sh..."
-cp "$SOURCE_DIR/hermes/autorun.sh" "$WORKDIR/squashfs-root/hermes/autorun.sh"
+cp "$SOURCE_DIR/hermes/autorun.sh" "$WORKDIR/squashfs-root/opt/hermes/autorun.sh"
 ok "autorun.sh updated"
 
 info "Re-packing squashfs..."
@@ -92,5 +93,5 @@ iso_size=$(du -h "$OUTPUT_ISO" | cut -f1)
 ok "ISO generated: $OUTPUT_ISO ($iso_size)"
 
 info "Cleaning up..."
-rm -rf "$WORKDIR"
+# rm -rf workdir (skip - bind mount)
 ok "Done!"