diff --git a/hermes/deploy.ps1 b/hermes/deploy.ps1
index 457511a..6c4c2fa 100644
--- a/hermes/deploy.ps1
+++ b/hermes/deploy.ps1
@@ -134,15 +134,27 @@ foreach ($Attempt in 1..3) {
     Start-Sleep -Seconds 5
 }
 if (-not $PullOk) {
-    Err 'Fallo la descarga del modelo tras 3 intentos.'
-    if (-not $env:HTTPS_PROXY) {
-        Write-Host '  Tu red no llega al registry de Ollama. Si tienes proxy/VPN, lanzalo y:'
-        Write-Host '    $env:HTTPS_PROXY = "http://127.0.0.1:7890"   # (ajusta al puerto de tu proxy)'
-        Write-Host '    .\deploy.ps1 vps'
+    # --- Fallback: mismo modelo via HuggingFace (otro CDN, no el registry de Ollama) ---
+    Warn 'Registry de Ollama no accesible. Probando via HuggingFace (mismo modelo)...'
+    $Gguf = Join-Path $ScriptDir 'llama3.2-3b-q4.gguf'
+    curl.exe -L -# --retry 3 --max-time 1800 -o "$Gguf" 'https://huggingface.co/bartowski/Llama-3.2-3B-Instruct-GGUF/resolve/main/Llama-3.2-3B-Instruct-Q4_K_M.gguf'
+    if ($LASTEXITCODE -eq 0 -and (Get-Item $Gguf).Length -gt 1900000000) {
+        docker cp "$Gguf" d0a1-hermes-ollama:/root/.ollama/import.gguf
+        docker exec d0a1-hermes-ollama sh -c 'echo FROM /root/.ollama/import.gguf > /tmp/mf && ollama create llama3.2:3b -f /tmp/mf'
+        $CreateOk = ($LASTEXITCODE -eq 0)
+        docker exec d0a1-hermes-ollama rm -f /root/.ollama/import.gguf | Out-Null
+        Remove-Item "$Gguf" -Force -ErrorAction SilentlyContinue
+        if ($CreateOk) { $PullOk = $true }
+        else { Err 'Fallo al importar el modelo desde el GGUF.' }
+    } else {
+        Err 'No se pudo descargar el modelo (ni registry ni HuggingFace).'
+        if (-not $env:HTTPS_PROXY) {
+            Write-Host '  Tu red bloquea ambos. Si tienes proxy/VPN:'
+            Write-Host '    $env:HTTPS_PROXY = "http://127.0.0.1:7890"   # (puerto de tu proxy)'
+            Write-Host '    .\deploy.ps1 vps'
+        }
+        exit 1
     }
-    Write-Host '  O reintenta a mano:'
-    Write-Host '  docker exec d0a1-hermes-ollama ollama pull llama3.2:3b'
-    exit 1
 }
 Ok "Ollama corriendo en http://localhost:${OllamaPort}"
 
diff --git a/openclaw/deploy.ps1 b/openclaw/deploy.ps1
index e624b4b..2907e0a 100644
--- a/openclaw/deploy.ps1
+++ b/openclaw/deploy.ps1
@@ -134,15 +134,27 @@ foreach ($Attempt in 1..3) {
     Start-Sleep -Seconds 5
 }
 if (-not $PullOk) {
-    Err 'Fallo la descarga del modelo tras 3 intentos.'
-    if (-not $env:HTTPS_PROXY) {
-        Write-Host '  Tu red no llega al registry de Ollama. Si tienes proxy/VPN, lanzalo y:'
-        Write-Host '    $env:HTTPS_PROXY = "http://127.0.0.1:7890"   # (ajusta al puerto de tu proxy)'
-        Write-Host '    .\deploy.ps1 vps'
+    # --- Fallback: mismo modelo via HuggingFace (otro CDN, no el registry de Ollama) ---
+    Warn 'Registry de Ollama no accesible. Probando via HuggingFace (mismo modelo)...'
+    $Gguf = Join-Path $ScriptDir 'llama3.2-3b-q4.gguf'
+    curl.exe -L -# --retry 3 --max-time 1800 -o "$Gguf" 'https://huggingface.co/bartowski/Llama-3.2-3B-Instruct-GGUF/resolve/main/Llama-3.2-3B-Instruct-Q4_K_M.gguf'
+    if ($LASTEXITCODE -eq 0 -and (Get-Item $Gguf).Length -gt 1900000000) {
+        docker cp "$Gguf" d0a1-openclaw-ollama:/root/.ollama/import.gguf
+        docker exec d0a1-openclaw-ollama sh -c 'echo FROM /root/.ollama/import.gguf > /tmp/mf && ollama create llama3.2:3b -f /tmp/mf'
+        $CreateOk = ($LASTEXITCODE -eq 0)
+        docker exec d0a1-openclaw-ollama rm -f /root/.ollama/import.gguf | Out-Null
+        Remove-Item "$Gguf" -Force -ErrorAction SilentlyContinue
+        if ($CreateOk) { $PullOk = $true }
+        else { Err 'Fallo al importar el modelo desde el GGUF.' }
+    } else {
+        Err 'No se pudo descargar el modelo (ni registry ni HuggingFace).'
+        if (-not $env:HTTPS_PROXY) {
+            Write-Host '  Tu red bloquea ambos. Si tienes proxy/VPN:'
+            Write-Host '    $env:HTTPS_PROXY = "http://127.0.0.1:7890"   # (puerto de tu proxy)'
+            Write-Host '    .\deploy.ps1 vps'
+        }
+        exit 1
     }
-    Write-Host '  O reintenta a mano:'
-    Write-Host '  docker exec d0a1-openclaw-ollama ollama pull llama3.2:3b'
-    exit 1
 }
 Ok "Ollama corriendo en http://localhost:${OllamaPort}"
 
diff --git a/openwebui/deploy.ps1 b/openwebui/deploy.ps1
index 2f529a1..6336f13 100644
--- a/openwebui/deploy.ps1
+++ b/openwebui/deploy.ps1
@@ -151,15 +151,27 @@ foreach ($Attempt in 1..3) {
     Start-Sleep -Seconds 5
 }
 if (-not $PullOk) {
-    Err 'Fallo la descarga del modelo tras 3 intentos.'
-    if (-not $env:HTTPS_PROXY) {
-        Write-Host '  Tu red no llega al registry de Ollama. Si tienes proxy/VPN, lanzalo y:'
-        Write-Host '    $env:HTTPS_PROXY = "http://127.0.0.1:7890"   # (ajusta al puerto de tu proxy)'
-        Write-Host '    .\deploy.ps1 vps'
+    # --- Fallback: mismo modelo via HuggingFace (otro CDN, no el registry de Ollama) ---
+    Warn 'Registry de Ollama no accesible. Probando via HuggingFace (mismo modelo)...'
+    $Gguf = Join-Path $ScriptDir 'llama3.2-3b-q4.gguf'
+    curl.exe -L -# --retry 3 --max-time 1800 -o "$Gguf" 'https://huggingface.co/bartowski/Llama-3.2-3B-Instruct-GGUF/resolve/main/Llama-3.2-3B-Instruct-Q4_K_M.gguf'
+    if ($LASTEXITCODE -eq 0 -and (Get-Item $Gguf).Length -gt 1900000000) {
+        docker cp "$Gguf" d0a1-ollama:/root/.ollama/import.gguf
+        docker exec d0a1-ollama sh -c 'echo FROM /root/.ollama/import.gguf > /tmp/mf && ollama create llama3.2:3b -f /tmp/mf'
+        $CreateOk = ($LASTEXITCODE -eq 0)
+        docker exec d0a1-ollama rm -f /root/.ollama/import.gguf | Out-Null
+        Remove-Item "$Gguf" -Force -ErrorAction SilentlyContinue
+        if ($CreateOk) { $PullOk = $true }
+        else { Err 'Fallo al importar el modelo desde el GGUF.' }
+    } else {
+        Err 'No se pudo descargar el modelo (ni registry ni HuggingFace).'
+        if (-not $env:HTTPS_PROXY) {
+            Write-Host '  Tu red bloquea ambos. Si tienes proxy/VPN:'
+            Write-Host '    $env:HTTPS_PROXY = "http://127.0.0.1:7890"   # (puerto de tu proxy)'
+            Write-Host '    .\deploy.ps1 vps'
+        }
+        exit 1
     }
-    Write-Host '  O reintenta a mano:'
-    Write-Host '  docker exec d0a1-ollama ollama pull llama3.2:3b'
-    exit 1
 }
 
 # --- Done -------------------------------------------------------------------
diff --git a/wordpress/deploy.ps1 b/wordpress/deploy.ps1
index e09446d..d6355c1 100644
--- a/wordpress/deploy.ps1
+++ b/wordpress/deploy.ps1
@@ -187,15 +187,27 @@ foreach ($Attempt in 1..3) {
     Start-Sleep -Seconds 5
 }
 if (-not $PullOk) {
-    Err 'Fallo la descarga del modelo tras 3 intentos.'
-    if (-not $env:HTTPS_PROXY) {
-        Write-Host '  Tu red no llega al registry de Ollama. Si tienes proxy/VPN, lanzalo y:'
-        Write-Host '    $env:HTTPS_PROXY = "http://127.0.0.1:7890"   # (ajusta al puerto de tu proxy)'
-        Write-Host '    .\deploy.ps1 vps'
+    # --- Fallback: mismo modelo via HuggingFace (otro CDN, no el registry de Ollama) ---
+    Warn 'Registry de Ollama no accesible. Probando via HuggingFace (mismo modelo)...'
+    $Gguf = Join-Path $ScriptDir 'llama3.2-3b-q4.gguf'
+    curl.exe -L -# --retry 3 --max-time 1800 -o "$Gguf" 'https://huggingface.co/bartowski/Llama-3.2-3B-Instruct-GGUF/resolve/main/Llama-3.2-3B-Instruct-Q4_K_M.gguf'
+    if ($LASTEXITCODE -eq 0 -and (Get-Item $Gguf).Length -gt 1900000000) {
+        docker cp "$Gguf" d0a1-wp-ollama:/root/.ollama/import.gguf
+        docker exec d0a1-wp-ollama sh -c 'echo FROM /root/.ollama/import.gguf > /tmp/mf && ollama create llama3.2:3b -f /tmp/mf'
+        $CreateOk = ($LASTEXITCODE -eq 0)
+        docker exec d0a1-wp-ollama rm -f /root/.ollama/import.gguf | Out-Null
+        Remove-Item "$Gguf" -Force -ErrorAction SilentlyContinue
+        if ($CreateOk) { $PullOk = $true }
+        else { Err 'Fallo al importar el modelo desde el GGUF.' }
+    } else {
+        Err 'No se pudo descargar el modelo (ni registry ni HuggingFace).'
+        if (-not $env:HTTPS_PROXY) {
+            Write-Host '  Tu red bloquea ambos. Si tienes proxy/VPN:'
+            Write-Host '    $env:HTTPS_PROXY = "http://127.0.0.1:7890"   # (puerto de tu proxy)'
+            Write-Host '    .\deploy.ps1 vps'
+        }
+        exit 1
     }
-    Write-Host '  O reintenta a mano:'
-    Write-Host '  docker exec d0a1-wp-ollama ollama pull llama3.2:3b'
-    exit 1
 }
 
 # --- Done -------------------------------------------------------------------