Add new model files and update Ansible playbooks for Qwen3.5 and Qwen3.6

- Created model files for Qwen3.5 with different context lengths.
- Added a new Ansible host variable file for CI server configuration.
- Updated GPU server host variables to include Ollama models and model files.
- Enhanced playbooks for Podman to manage Ollama models, including copying model files and checking existing models.
- Introduced a new playbook for setting up Qwen3.6 with specific configurations.
- Updated Windows SSH tasks to improve security and configuration management.
- Added a Python utility to parse Ollama model names from command output.
- Modified Terraform configurations to include new DNS entries and proxy settings.
- Improved Nginx proxy configurations with timeout settings.

ansible/host_vars/gpu-01.lab.alexpires.me.yml

@@ -107,3 +107,35 @@ certbot_domains:
   - "gpu-01.lab.alexpires.me"
 
 certbot_cockpit_domain: "gpu-01.lab.alexpires.me"
+ollama_models:
+  # Thinking models
+  - gpt-oss:latest
+  - gemma4:e4b
+  - qwen3.5:9b
+  - qwen3.5:4b
+  # Non-thinking models
+  - ministral-3:3b
+  - ministral-3:8b
+  - ministral-3:14b
+  - granite4.1:3b
+  - granite4.1:8b
+  - deepseek-r1:latest
+  - qwen2.5-coder:3b
+  # Embedding models
+  - embeddinggemma:latest
+  - nomic-embed-text:latest
+  # Whisper models
+  - dimavz/whisper-tiny:latest
+ollama_model_files:
+  - file: "ollama/gpt-oss-latest-32k.modelfile"
+    name: "gpt-oss-32k:latest"
+  - file: "ollama/gemma4-e4b-32k.modelfile"
+    name: "gemma4-e4b-32k:latest"
+  - file: "ollama/qwen3.5-9b-32k.modelfile"
+    name: "qwen3.5-9b-32k:latest"
+  - file: "ollama/qwen3.5-9b-64k.modelfile"
+    name: "qwen3.5-9b-64k:latest"
+  - file: "ollama/qwen3.5-4b-32k.modelfile"
+    name: "qwen3.5-4b-32k:latest"
+  - file: "ollama/qwen3.5-4b-64k.modelfile"
+    name: "qwen3.5-4b-64k:latest"