{
 "slug": "ollama",
 "name": "Ollama + Open WebUI",
 "tagline": "Run open LLMs locally with a REST API and a ChatGPT-like web interface",
 "category": "ai-llm",
 "use_cases": [
  "llm-inference",
  "chat-ui",
  "private-llm"
 ],
 "aliases": [
  "open webui",
  "ollama open webui"
 ],
 "status": "live",
 "upstream": {
  "vendor": "Open WebUI",
  "url": "https://openwebui.com",
  "license": "MIT",
  "license_url": "https://github.com/ollama/ollama/blob/main/LICENSE"
 },
 "image": {
  "os": "Ubuntu 24.04 LTS",
  "cis_level": 1,
  "ports": [
   80,
   443
  ],
  "artifacts": [
   "/etc/lynxroute/sbom.json",
   "/etc/lynxroute/cis-report.html",
   "/usr/share/doc/lynxroute/CIS_TAILORED_PROFILE.md"
  ]
 },
 "clouds": {
  "aws": {
   "status": "live",
   "version": "0.40.11",
   "last_build": "2026-10-25",
   "entity_id": "prod-ujhbnz5tfcyt4",
   "ami_alias": "/aws/service/marketplace/prod-ujhbnz5tfcyt4/latest",
   "listing_url": "https://aws.amazon.com/marketplace/pp/prodview-6vnvbpyso464e",
   "recommended_instance_type": "t3.medium",
   "price_usd_per_hour": 0.05,
   "free_trial_days": 5,
   "unit": "instance-hour"
  },
  "azure": {
   "status": "live",
   "version": "0.35.0",
   "last_build": "2026-10-02",
   "offer_id": "ollama",
   "plan_id": "payg-gen2",
   "image_urn": "lynxroute:ollama:payg-gen2:latest",
   "listing_url": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/lynxroute.ollama?tab=Overview",
   "recommended_vm_size": "Standard_D2s_v3",
   "price_usd_per_vcpu_hour": 0.028,
   "unit": "vcpu-hour"
  },
  "alicloud": {
   "status": "not_offered"
  }
 },
 "urls": {
  "page": "https://lynxroute.com/products/ollama/",
  "json": "https://lynxroute.com/products/ollama/product.json"
 },
 "release_notes": [
  {
   "version": "0.40.11",
   "title": "Ollama 0.40.11 + Open WebUI 0.12.4",
   "notes": "* Ollama updated 0.35.0 -> 0.40.11. MIT unchanged. Adds decision models (yes/no, classification and scoring via ollama run --ask), new model families, faster inference by reusing loaded models, and more reliable OpenAI-compatible streaming\n* Security: bundled Open WebUI updated 0.11.4 -> 0.12.4, picking up the upstream security fixes in 0.12.x, including channel message spoofing (GHSA-3vvh-g22g-jq6r) and a cryptographically secure generated secret key. Open WebUI License unchanged, branding intact\n* Hardening: Open WebUI's session-signing key is now unique to each instance, generated on first boot\n* Rebuilt on the latest CIS Level 1 hardened Ubuntu 24.04 LTS base, picking up every operating-system security update published since the previous build\n",
   "source": "backfill-aws-listing",
   "live": {
    "aws": "2026-10-25"
   }
  },
  {
   "version": "0.35.0",
   "title": "Ollama 0.35.0 + Open WebUI 0.11.4",
   "notes": "* Security: bundled Open WebUI updated to 0.11.4, fixing published advisories including session-token theft by any website (GHSA-vpq8-f445-hcq7), token theft through DOCX previews (GHSA-f9xp-mfmq-x6cg) and citation links (GHSA-qpqv-xwg8-cqpj), and a terminal-proxy privilege escalation (GHSA-q46m-r89w-j74p)\n* Ollama remains at 0.35.0. MIT unchanged; Open WebUI remains under the Open WebUI License with its branding intact\n* Rebuilt on the latest CIS Level 1 hardened Ubuntu 24.04 LTS base, picking up every operating-system security update published since the previous build\n",
   "source": "backfill-aws-listing",
   "live": {
    "aws": "2026-10-23",
    "azure": "2026-10-02"
   }
  },
  {
   "version": "0.35.0",
   "title": "Ollama 0.35.0 + Open WebUI 0.11.3",
   "notes": "* Ollama updated 0.34.2 -> 0.35.0. MIT unchanged. Bundled Open WebUI stays at 0.11.3\n* Adds support for decision models, which answer with choices, probabilities and scores instead of text, for tasks such as ticket triage and classification\n* Structured outputs on thinking models now apply in a single pass, and model details now show each model's thinking controls\n* Fixes intermittent \"model not found\" errors with a large model library and model pulls from Hugging Face; requests using the deprecated typical_p option now log a warning instead of failing; updated llama.cpp engine\n* Model storage, manifest format and the /api/generate, /api/chat and /v1/chat/completions endpoints are unchanged, so models already pulled on an existing instance keep working\n* Certbot pre-installed - enable a trusted HTTPS certificate with one command: sudo certbot --nginx -d yourdomain.com\n* Rebuilt on the current CIS Level 1 hardened Ubuntu 24.04 LTS base for the latest Ubuntu security updates\n",
   "source": "backfill-aws-listing",
   "live": {
    "aws": "2026-10-23",
    "azure": "2026-10-02"
   }
  },
  {
   "version": "0.34.2",
   "title": "Ollama 0.34.2 + Open WebUI 0.11.3",
   "notes": "* Ollama updated 0.34.1 -> 0.34.2, a patch release. MIT unchanged. Bundled Open WebUI stays at 0.11.3\n* The ollama command line now opens a first-run setup with the option to sign in or continue locally - no account is required to use this instance\n* Redirect handling for model registry requests has been tightened\n* Fixed excessive memory growth during long generations with MLX speculative decoding\n* Updated llama.cpp engine\n* Model storage, manifest format and the /api/generate, /api/chat and /v1/chat/completions endpoints are unchanged, so models already pulled on an existing instance keep working\n* Certbot pre-installed - enable a trusted HTTPS certificate with one command: sudo certbot --nginx -d yourdomain.com\n* Rebuilt on the current CIS Level 1 hardened Ubuntu 24.04 LTS base for the latest Ubuntu security updates\n",
   "source": "backfill-aws-listing",
   "live": {
    "aws": "2026-09-20",
    "azure": "2026-09-21"
   }
  },
  {
   "version": "0.34.1",
   "title": "Ollama 0.34.1 + Open WebUI 0.11.3",
   "notes": "* Ollama updated 0.34.0 -> 0.34.1, a patch release. MIT unchanged. Bundled Open WebUI stays at 0.11.3\n* /api/tags is much faster on large model libraries, and model capabilities are now reported consistently\n* Runaway repeat-token detection now needs 100 repeated tokens, reducing false positives on OCR-style output, and returns an error instead of silently closing the response\n* ollama create no longer converts or quantizes safetensors into GGUF - use llama.cpp tooling for that; importing existing GGUF files is unchanged. The typical_p parameter is deprecated for newly created models\n* The built-in CLI agent is removed; ollama run returns to the classic chat interface\n* Updated llama.cpp and MLX engines\n* Model storage, manifest format and the /api/generate, /api/chat and /v1/chat/completions endpoints are unchanged, so models already pulled on an existing instance keep working\n* Certbot pre-installed - enable a trusted HTTPS certificate with one command: sudo certbot --nginx -d yourdomain.com\n* Rebuilt on the current CIS Level 1 hardened Ubuntu 24.04 LTS base for the latest Ubuntu security updates\n",
   "source": "backfill-aws-listing",
   "live": {
    "aws": "2026-09-17",
    "azure": "2026-09-18"
   }
  },
  {
   "version": "0.34.0",
   "title": "Ollama 0.34.0 + Open WebUI 0.11.3",
   "notes": "* Ollama updated 0.33.3 -> 0.34.0, a minor release. MIT unchanged. Bundled Open WebUI stays at 0.11.3\n* The OpenAI-compatible /v1/responses endpoint gains automatic response compaction and a new /v1/responses/compact route, so long tool-using sessions keep working once they outgrow the model context window\n* Adds client tool-search support on the OpenAI-compatible API, and images now survive compaction intact\n* Fixes data races in the download-progress and scheduler paths\n* Model storage, manifest format and the /api/generate, /api/chat and /v1/chat/completions endpoints are unchanged, so models already pulled on an existing instance keep working\n* Certbot pre-installed - enable a trusted HTTPS certificate with one command: sudo certbot --nginx -d yourdomain.com\n* Rebuilt on the current CIS Level 1 hardened Ubuntu 24.04 LTS base for the latest Ubuntu security updates\n",
   "source": "backfill-aws-listing",
   "live": {
    "aws": "2026-09-11",
    "azure": "2026-09-13"
   }
  },
  {
   "version": "0.33.3",
   "title": "Ollama 0.33.3 + Open WebUI 0.11.3",
   "notes": "* Ollama upgraded to 0.33.3 (from 0.32.15) and Open WebUI to 0.11.3 (from 0.9.6)\n* Open WebUI ships a rebuilt interface - a narrower conversation column, lighter typography, consistent menus and dropdowns, and a rearranged settings and admin panel\n* Open WebUI adds folder sharing with per-user, per-group and read-or-write access, automatic context compaction for long conversations (off by default), and much faster hybrid search over large knowledge bases\n* Ollama prompt-prefill caching is now reliable across cancelled and resumed requests, so a retried request continues from where it stopped instead of reprocessing the whole prompt\n* Ollama reports cached prompt tokens and honours the default parameters declared by a GGUF model\n* Certbot pre-installed - enable a trusted HTTPS certificate with one command: sudo certbot --nginx -d yourdomain.com\n* Rebuilt on the latest CIS Level 1 hardened Ubuntu 24.04 LTS base\n",
   "source": "backfill-aws-listing",
   "live": {
    "aws": "2026-09-06",
    "azure": "2026-09-09"
   }
  },
  {
   "version": "0.32.15",
   "title": "Ollama 0.32.15 + Open WebUI 0.9.6",
   "notes": "* Ollama upgraded to 0.32.15 (from 0.32.14) - patch release. Open WebUI remains at 0.9.6; the client API surface is unchanged\n* Resolved model metadata is cached between requests, roughly halving time-to-first-token in upstream benchmarks\n* Fixes chat and generate wedging after a mid-stream parser error, and normalises non-leading system messages for the Qwen 3.8 renderer\n* Certbot pre-installed - enable a trusted HTTPS certificate with one command: sudo certbot --nginx -d yourdomain.com\n* Rebuilt on the latest CIS Level 1 hardened Ubuntu 24.04 LTS base\n",
   "source": "backfill-aws-listing",
   "live": {
    "aws": "2026-08-23"
   }
  },
  {
   "version": "0.32.14",
   "title": "Ollama 0.32.14 + Open WebUI 0.9.6",
   "notes": "* Ollama upgraded to 0.32.14 (from 0.32.3) - rolls up the 0.32.x patch line, including WebP image transcoding for llama-server and tolerance of non-leading system messages in the Qwen renderer. Open WebUI remains at 0.9.6; the client API surface is unchanged.\n* Certbot pre-installed - enable a trusted HTTPS certificate with one command: sudo certbot --nginx -d yourdomain.com\n* Rebuilt on the latest CIS Level 1 hardened Ubuntu 24.04 LTS base\n",
   "source": "backfill-git",
   "live": {
    "aws": "2026-08-18",
    "azure": "2026-08-19"
   }
  },
  {
   "version": "0.32.3",
   "title": "Ollama 0.32.3 + Open WebUI 0.9.6",
   "notes": "* Ollama upgraded to 0.32.3 (from 0.32.1) - fixes stalled model downloads, adds GPU/model support, and includes upstream bugfixes (0.32.2 was withdrawn upstream). Open WebUI remains at 0.9.6; the client API surface is unchanged.\n* Certbot pre-installed - enable a trusted HTTPS certificate with one command: sudo certbot --nginx -d yourdomain.com\n* Rebuilt on the latest CIS Level 1 hardened Ubuntu 24.04 LTS base\n",
   "source": "backfill-git",
   "live": {
    "aws": "2026-07-24",
    "azure": "2026-07-27"
   }
  },
  {
   "version": "0.32.1",
   "title": "Ollama 0.32.1 + Open WebUI 0.9.6",
   "notes": "* Ollama upgraded to 0.32.1 (from 0.31.2); improved model tool-calling and multi-turn handling, an interactive agent experience, and an MLX cache memory-leak fix. Open WebUI remains at 0.9.6; the client API surface is unchanged.\n* Certbot pre-installed - enable a trusted HTTPS certificate with one command: sudo certbot --nginx -d yourdomain.com\n* Rebuilt on the latest CIS Level 1 hardened Ubuntu 24.04 LTS base\n",
   "source": "backfill-aws-listing",
   "live": {
    "aws": "2026-07-20",
    "azure": "2026-07-20"
   }
  },
  {
   "version": "0.31.2",
   "title": "Ollama 0.31.2 + Open WebUI 0.9.6",
   "notes": "* Ollama upgraded to 0.31.2 (from 0.30.10); updated llama.cpp inference engine, flash attention on older NVIDIA GPUs (compute capability 6.x), iGPU vision-model offload, and structured-output fixes. Open WebUI remains at 0.9.6; the client API surface is unchanged.\n* Certbot pre-installed - enable a trusted HTTPS certificate with one command: sudo certbot --nginx -d yourdomain.com\n* Rebuilt on the latest CIS Level 1 hardened Ubuntu 24.04 LTS base\n",
   "source": "backfill-aws-listing",
   "live": {
    "aws": "2026-07-11",
    "azure": "2026-07-11"
   }
  },
  {
   "version": "0.30.10",
   "title": "Ollama + Open WebUI 0.30.10 - June 2026",
   "notes": "* Ollama upgraded to 0.30.10 (from 0.30.8); updated llama.cpp inference engine (build 9672), broader model-architecture support (Cohere2Moe; Command A / North on Apple Silicon via MLX), improved prompt-cache reuse and error handling. Open WebUI remains at 0.9.6.\n* Certbot pre-installed - enable a trusted HTTPS certificate with one command: sudo certbot --nginx -d yourdomain.com\n* Rebuilt on the latest CIS Level 1 hardened Ubuntu 24.04 LTS base\n",
   "source": "backfill-aws-listing",
   "live": {
    "aws": "2026-06-24",
    "azure": "2026-06-20"
   }
  },
  {
   "version": "0.30.8",
   "title": "Ollama + Open WebUI 0.30.8 - June 2026",
   "notes": "* Ollama upgraded to 0.30.8 (from 0.30.6); prompt-cache decoupled from context shift, hardened MLX layers, improved recurrent-model support. Open WebUI 0.9.6.\n* Certbot pre-installed for one-command trusted HTTPS\n",
   "source": "backfill-aws-listing",
   "live": {
    "aws": "2026-06-16"
   }
  },
  {
   "version": "0.30.6",
   "title": "Ollama + Open WebUI 0.30.6 - June 2026",
   "notes": "* Ollama upgraded from 0.24 to 0.30.6: performance and quantization\n  improvements, new integrations, and bug fixes\n* Open WebUI updated to the latest release\n",
   "source": "backfill-aws-listing",
   "live": {
    "aws": "2026-06-06",
    "azure": "2026-06-07"
   }
  },
  {
   "version": "0.9.5",
   "title": "Ollama + Open WebUI 0.9.5 - May 2026",
   "notes": "* Open WebUI 0.9.5 + Ollama 0.24.0 on Ubuntu 24.04 LTS\n* OWUI security release - redirect-based SSRF protection (block 3xx redirects\n  via AIOHTTP_CLIENT_ALLOW_REDIRECTS), iframe Content-Security-Policy\n  (IFRAME_CSP), URL parser SSRF bypass fix, image URL SSRF, file ownership\n  checks on folder/knowledge attachments, permission enforcement for\n  skills/calendars/channels/feedback, profile image MIME-type allowlist\n* New OWUI: granular markdown rendering controls, channel streaming + tool\n  support, terminal proxy response headers, model params hidden for read-only\n* Ollama 0.24.0: Codex App support (OpenAI desktop experience), built-in\n  browser for local servers, review mode for in-app code comments\n",
   "source": "backfill-aws-listing",
   "live": {
    "aws": "2026-05-23"
   }
  },
  {
   "version": "0.9.2",
   "title": "Ollama + Open WebUI 0.9.2 - Initial release (April 2026)",
   "notes": "* Ollama 0.21.2 + Open WebUI 0.9.2 on Ubuntu 24.04 LTS\n* Nginx HTTPS, startup page (~2-3 min), models not pre-loaded\n* SBOM, CIS Report, IMDSv2 enforced\n",
   "source": "backfill-aws-listing",
   "live": {
    "aws": "2026-04-25"
   }
  }
 ],
 "release_history": [
  {
   "version": "0.40.11",
   "aws": "2026-10-25"
  },
  {
   "version": "0.35.0",
   "aws": "2026-10-23",
   "azure": "2026-10-02"
  },
  {
   "version": "0.34.2",
   "aws": "2026-09-20",
   "azure": "2026-09-21"
  },
  {
   "version": "0.34.1",
   "aws": "2026-09-17",
   "azure": "2026-09-18"
  },
  {
   "version": "0.34.0",
   "aws": "2026-09-11",
   "azure": "2026-09-13"
  },
  {
   "version": "0.33.3",
   "aws": "2026-09-06",
   "azure": "2026-09-09"
  },
  {
   "version": "0.32.15",
   "aws": "2026-08-23"
  },
  {
   "version": "0.32.14",
   "aws": "2026-08-18",
   "azure": "2026-08-19"
  },
  {
   "version": "0.32.3",
   "aws": "2026-07-24",
   "azure": "2026-07-27"
  },
  {
   "version": "0.32.1",
   "aws": "2026-07-20",
   "azure": "2026-07-20"
  },
  {
   "version": "0.31.2",
   "aws": "2026-07-11",
   "azure": "2026-07-11"
  },
  {
   "version": "0.30.10",
   "aws": "2026-06-24",
   "azure": "2026-06-20"
  },
  {
   "version": "0.30.8",
   "aws": "2026-06-16"
  },
  {
   "version": "0.30.6",
   "aws": "2026-06-06",
   "azure": "2026-06-07"
  },
  {
   "version": "0.9.5",
   "aws": "2026-05-23"
  },
  {
   "version": "0.9.2",
   "aws": "2026-04-25"
  }
 ],
 "deploy": {
  "aws_cli": "# subscribe once on the AWS Marketplace listing, then:\naws ec2 run-instances \\\n  --image-id resolve:ssm:/aws/service/marketplace/prod-ujhbnz5tfcyt4/latest \\\n  --instance-type t3.medium --key-name my-key --security-group-ids sg-xxxxxxxx",
  "azure_cli": "# accept the plan terms once, then:\naz vm image terms accept --publisher lynxroute --offer ollama --plan payg-gen2\naz vm create -g my-rg -n ollama --size Standard_D2s_v3 \\\n  --image lynxroute:ollama:payg-gen2:latest --admin-username azureuser --generate-ssh-keys"
 },
 "description": {
  "what_is": "Ollama is a Go-based runtime for running large language models locally - it pulls quantized GGUF weights from the public Ollama library and exposes a streaming REST API for inference with optional GPU acceleration via NVIDIA CUDA. Open WebUI is a self-hosted ChatGPT-style web interface (FastAPI + Svelte) that connects to the local Ollama API and lets your team chat with models, manage conversations, upload documents for RAG, run web search, and configure prompt templates. The bundle supports CPU and GPU instance types (g4dn.xlarge, g5.xlarge), embedded SQLite for chat history and user accounts, and Llama, Mistral, Gemma, Phi, Qwen, DeepSeek-R1 and 100+ models pulled on demand. Together they form a complete private AI stack with no external service dependencies.\n\nLICENSING NOTE\n\nOllama is MIT-licensed. Open WebUI is distributed under the source-available Open WebUI License (not an OSI-approved open-source license). The license permits self-hosted use without restriction; deployments with more than 50 end users in any 30-day window that also modify Open WebUI branding (name, logo) require a commercial Enterprise License from Open WebUI Inc. This image ships Open WebUI with the original branding preserved - the 50-user clause does not apply unless the operator rebrands.",
  "image_adds": "Security hardening:\n* Authentication enabled by default\n* Nginx reverse proxy with TLS - Open WebUI proxied on port 443\n* Ollama API (port 11434) bound to localhost only\n* UFW firewall - ports 22, 80, 443 only\n* fail2ban, AppArmor\n\nOS hardening (CIS Level 1):\n* CIS Ubuntu 24.04 LTS Level 1 benchmark applied via ansible-lockdown\n* auditd, SSH hardening, Kernel hardening, IMDSv2 enforced\n\nCompliance artifacts:\n* SBOM - CycloneDX 1.6 at /etc/lynxroute/sbom.json\n* CIS Conformance Report at /etc/lynxroute/cis-report.html\n* CIS Tailored Profile at /usr/share/doc/lynxroute/CIS_TAILORED_PROFILE.md"
 },
 "generated_at": "2026-10-31T09:36:34Z"
}