{ "data": { "a": { "slug": "docker-model-runner", "name": "Docker Model Runner", "vendor": "Docker, Inc.", "vendorUrl": "https://www.docker.com", "kind": "http-api", "category": "local-ai", "summary": "Docker's open-source tool for pulling and running open models from Docker Hub, OCI registries or Hugging Face. It runs through Docker Desktop, Docker Engine or a standalone `dmr` binary, with local OpenAI-, Anthropic- and Ollama-compatible APIs.", "url": "https://www.anchorterminal.com/tools/docker-model-runner", "markdownUrl": "https://www.anchorterminal.com/tools/docker-model-runner.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/docker-model-runner.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/docker-model-runner.json", "repo": "https://github.com/docker/model-runner", "license": "Apache-2.0 (server, CLI plugin and `dmr` binary). Docker Desktop, which bundles it, is closed software under Docker's subscription agreement, and each model carries its own licence", "transports": [ "http" ], "packages": [ { "registry": "oci", "name": "docker.io/docker/model-runner" } ], "auth": "none", "authNotes": "The API takes no credential, and the docs say it ignores any key sent. Per the docs, any client that can reach it, including other containers on the same Docker network, can pull, load and run models. In Docker Desktop, host-side TCP is off until enabled in settings or with `docker desktop enable model-runner --tcp \u003cport\u003e`, and containers reach the API at model-runner.docker.internal. In Docker Engine, TCP is on by default on port 12434. Cross-origin requests get 403 unless the origin is localhost, 127.0.0.1, 0.0.0.0 or listed in `DMR_ORIGINS` (https://docs.docker.com/ai/model-runner/; https://github.com/docker/model-runner/blob/main/pkg/envconfig/envconfig.go).", "pricing": "free", "pricingNotes": "Free under Apache-2.0, with no account needed for the Docker Engine plugin or the standalone `dmr` binary. On macOS and Windows it also ships inside Docker Desktop, which is free for personal use, non-commercial open-source projects and businesses with fewer than 250 employees and under US $10,000,000 in annual revenue. Larger organisations need a paid Docker plan for Desktop (https://www.docker.com/legal/docker-subscription-service-agreement/; https://www.docker.com/pricing/, checked 2026-10-08).", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs or the source (checked 2026-10-08).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 656, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-08" }, "docsUrl": "https://docs.docker.com/ai/model-runner/", "llmsTxt": "https://docs.docker.com/llms.txt", "capabilities": [ "inference.local", "inference.open-weights", "inference.llm", "embed.text", "rerank", "image.generate" ], "tags": [ "open-source", "local", "self-hosted", "free", "no-card", "openai-compatible", "llms-txt", "docker", "go", "no-auth" ], "lastRelease": "2026-08-12", "graded": true, "anchor": { "graded": true, "score": 57.2, "grade": "C", "agentReady": false, "rank": 728, "ranked": true, "rankOf": 1239, "categoryRank": 10, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 58, "maintenance": 55, "payments": 60, "reliability": 85, "schema": 49, "security": 40, "transparency": 74 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-08" }, "negative": -3, "negativeNotes": [ "2026-02-27. GHSA-m456-c56c-hh5c (CVE-2026-28400, 7.5). The unauthenticated `/engines/_configure` route accepted arbitrary runtime flags, so a caller, including a container on Docker Desktop, could overwrite files the runner could reach, the Desktop VM disk among them. Fixed in Model Runner 1.0.16 and Docker Desktop 4.61.0 and published by Docker, more than six months ago, -2. https://github.com/docker/model-runner/security/advisories/GHSA-m456-c56c-hh5c", "2026-03-30. GHSA-x2f5-332j-9xwq (CVE-2026-33990, 7.1). A malicious OCI registry could point the token exchange at an internal URL and make the runner send GET requests to host-local services. Fixed in 1.1.25 and Docker Desktop 4.67.0 and published by Docker, more than six months ago, -1. https://github.com/docker/model-runner/security/advisories/GHSA-x2f5-332j-9xwq" ], "verdict": "CI passes on the main branch, and Docker has published two security advisories with CVEs and fixed versions for the project. The API takes no credential, so any client or container that reaches it can pull, delete and run models, and the documentation has no OpenAPI file or error reference.", "bestFor": "A team that already runs Docker and wants local models served to containers and Compose services through OpenAI-, Anthropic- or Ollama-compatible routes, with models stored as OCI artefacts.", "strengths": [ "OpenAI-, Anthropic- and Ollama-compatible routes on one local port, so existing clients for those three APIs work with a changed base URL", "CI runs lint, race-detector tests and end-to-end tests on every push to main, and the ten most recent runs on main passed on 8 October 2026", "Two GitHub security advisories with CVE numbers, fixed versions and workarounds, and a SECURITY.md that promises an acknowledgement within 72 hours", "Apache-2.0 source, and the docs list what usage data is collected with a link to the code that sends it", "Host-side TCP is off by default in Docker Desktop, and inference engines run sandboxed on macOS and Windows or in a container on Linux" ], "weaknesses": [ "No credential on the API. The docs say any client that can reach it, including other containers, can pull, load and run models", "No OpenAPI file, no error reference and no rate-limit or retry guidance in the reviewed documentation", "Two releases in the 90 days to 8 October 2026 (v1.2.7 and v1.2.8), the latest on 12 August", "CVE-2026-28400 let an unauthenticated caller overwrite files, including the Docker Desktop VM disk, until 1.0.16 in February 2026", "On Docker Engine the docs say model-name requests go to Docker Hub regardless of settings, and the `DO_NOT_TRACK` switch in the source is undocumented" ], "agentNotes": [ "Use base URL `http://localhost:12434/engines/v1` for OpenAI clients and `http://localhost:12434` for Anthropic and Ollama clients. Any API key value is accepted", "In Docker Desktop, run `docker desktop enable model-runner --tcp 12434` first. Host-side TCP is off by default", "From a container, call `http://model-runner.docker.internal` on Docker Desktop or `http://172.17.0.1:12434` on Docker Engine", "Raise the context before agent work with `docker model configure --context-size \u003cn\u003e \u003cmodel\u003e`. The llama.cpp default is 4,096 tokens", "Name models with their namespace, such as `ai/smollm2`, and expect plain-text error bodies with a 400, 404, 500 or 503 status" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 57.2 } ], "editorialScores": { "ergonomics": 58, "maintenance": 55, "payments": 60, "reliability": 85, "schema": 49, "security": 40, "transparency": 62 }, "provenanceScore": 86, "checked": { "categories": { "ergonomics": "2026-10-08", "maintenance": "2026-10-08", "payments": "2026-10-08", "reliability": "2026-10-08", "schema": "2026-10-08", "security": "2026-10-08", "transparency": "2026-10-08" }, "last": "2026-10-08", "lastMoved": "2026-10-27", "oldest": "2026-10-08", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "sudo apt-get update \u0026\u0026 sudo apt-get install docker-model-plugin # Docker Engine on Ubuntu or Debian; Docker Desktop: docker desktop enable model-runner --tcp 12434\ndocker model pull ai/smollm2", "http": "curl http://localhost:12434/engines/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -d '{\n \"model\": \"ai/smollm2\",\n \"messages\": [{\"role\": \"user\", \"content\": \"Say hello in one sentence.\"}]\n }'", "claudeCode": "docker model launch claude" }, "letme": { "capability": "https://letme.dev/inference.local", "tool": "https://letme.dev/docker-model-runner" }, "sameCompany": [ "docker-agent" ], "area": "models", "provenance": { "legalEntity": "Docker, Inc.", "domain": "docker.com", "domainRegistered": "1995-01-25", "endpointOnVendorDomain": null, "terms": "https://www.docker.com/legal/docker-subscription-service-agreement/", "privacy": "https://www.docker.com/legal/privacy/", "statusPage": "", "changelog": "https://github.com/docker/model-runner/releases", "securityTxt": "valid", "checked": "2026-10-08", "notes": [ "The repository is under GitHub's docker organisation and SECURITY.md sends reports to security@docker.com. The subscription agreement and privacy policy both name Docker, Inc.", "Docker publishes no terms written for Model Runner. The Docker Subscription Service Agreement (last updated 26 August 2026) governs Docker Desktop, which bundles it, and the privacy policy carries the same date. The Engine plugin and the `dmr` binary are under Apache-2.0 only.", "www.docker.com/.well-known/security.txt gives security@docker.com, a policy URL and an expiry of 1 January 2030.", "No status page is listed because the software runs on the owner's machine.", "RDAP for docker.com gives a registration date of 1995-01-25." ], "score": 86 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/docker-model-runner.json", "live": { "slug": "docker-model-runner", "versions": [ { "registry": "github", "name": "docker/model-runner", "version": "v1.2.9", "released": "2026-10-22", "seenAt": "2026-10-30T14:09:39.240595875Z" } ], "githubStars": 658, "securityTxt": { "url": "https://docker.com/.well-known/security.txt", "state": "valid", "expires": "2030-01-01T05:00:00.000Z", "checkedAt": "2026-10-30T15:39:28.677817795Z" }, "llmsTxt": { "url": "https://docs.docker.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-30T15:07:17.540288882Z" }, "domain": { "domain": "docker.com", "registered": "1995-01-25", "source": "https://rdap.verisign.com/com/v1/domain/docker.com", "checkedAt": "2026-10-25T14:02:09.027030725Z" }, "pages": [ { "url": "https://www.docker.com/pricing/", "kind": "pricing", "status": 200, "checkedAt": "2026-10-30T05:54:54.301823417Z", "changedAt": "2026-10-23T02:01:26.989616125Z", "fingerprint": "4fa0bc9e38a0" }, { "url": "https://www.docker.com/legal/docker-subscription-service-agreement/", "kind": "terms", "status": 200, "checkedAt": "2026-10-30T05:54:48.147831176Z", "changedAt": "2026-10-29T05:21:57.976837404Z", "fingerprint": "dc1264d42246" } ], "github": { "repo": "docker/model-runner", "checkedAt": "2026-10-26T07:24:00.851185412Z", "stars": 658, "archived": false, "issuesEnabled": true, "pushedAt": "2026-10-26T06:56:45Z", "openIssues": 41, "openPRs": 28, "issuesOpened90d": 16, "issuesClosed90d": 16, "prsMerged90d": 32, "ci": { "branch": "main", "runs": 50, "success": 48, "failure": 2, "other": 0, "latest": "success", "latestAt": "2026-10-25T21:18:22Z" }, "advisories": [ { "ghsa": "GHSA-x2f5-332j-9xwq", "cve": "CVE-2026-33990", "severity": "high", "published": "2026-03-30T10:26:25Z" }, { "ghsa": "GHSA-m456-c56c-hh5c", "cve": "CVE-2026-28400", "severity": "high", "published": "2026-02-27T16:33:09Z" } ], "replies": { "sampled": 25, "unanswered": 22, "medianDays": 6 } }, "updatedAt": "2026-10-30T15:39:28.677817795Z" } }, "answer": "Docker Model Runner and HyperQwen score within a point of each other on agent readiness, 57.2 (C) and 56.9 (C). HyperQwen leads on schema \u0026 documentation, agent ergonomics and maintenance \u0026 community.", "b": { "slug": "hyperqwen", "name": "HyperQwen", "vendor": "syv.ai (syv-ai on GitHub)", "vendorUrl": "https://syv.ai", "kind": "http-api", "category": "local-ai", "summary": "HyperQwen is syv.ai's open-source serving setup for Qwen3.8-27B on one 24 GB NVIDIA GPU. A patch series against a pinned vLLM, a requantisation pipeline and Docker Compose profiles run vLLM's OpenAI-compatible API on port 18020.", "url": "https://www.anchorterminal.com/tools/hyperqwen", "markdownUrl": "https://www.anchorterminal.com/tools/hyperqwen.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/hyperqwen.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/hyperqwen.json", "repo": "https://github.com/syv-ai/HyperQwen", "license": "Apache-2.0", "transports": [ "http" ], "packages": [ { "registry": "oci", "name": "ghcr.io/syv-ai/hyperqwen" } ], "auth": "none", "authNotes": "No credential by default. `VLLM_API_KEY` in `.env` (or an `api_key.txt` file) turns on vLLM's Bearer check. With no key, the launcher binds 127.0.0.1 outside a container, and Docker Compose publishes the port on 127.0.0.1 unless `BIND` is changed. With a key set, the launcher binds every interface. The key is vLLM's own, one static key with no scopes, which vLLM checks only under `/v1`, `/v2`, `/inference` and `/cohere` (per the vLLM listing's check of 9 October 2026, https://github.com/vllm-project/vllm/blob/main/docs/usage/security.md).", "pricing": "free", "pricingNotes": "Free under Apache-2.0 with no account, key or card. Nothing is sold. The README links a Ko-fi page for donations towards GPU time. The owner pays for a 24 GB NVIDIA GPU, about 40 GB of disk and electricity.", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the README, the docs or the launch scripts (checked 2026-10-30). Nothing is sold.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 2400, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-30" }, "docsUrl": "https://github.com/syv-ai/HyperQwen#readme", "capabilities": [ "inference.local", "inference.open-weights" ], "tags": [ "open-source", "local", "self-hosted", "free", "no-card", "apache-2.0", "openai-compatible", "docker", "tool-calling", "reasoning", "pre-1.0" ], "graded": true, "anchor": { "graded": true, "score": 56.9, "grade": "C", "agentReady": false, "rank": 738, "ranked": true, "rankOf": 1239, "categoryRank": 11, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 65, "maintenance": 68, "payments": 60, "reliability": 59, "schema": 56, "security": 41, "transparency": 55 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-30" }, "negative": 0, "verdict": "HyperQwen packages a patched vLLM 0.32.0 and requantised Qwen3.8-27B weights into one container with tool calling preset and a loopback bind when no key is set. It runs one model family, its speed figures come from one RTX 3090, and it has no versioned releases, changelog or security policy.", "bestFor": "An operator with one 24 GB NVIDIA card who wants Qwen3.8-27B behind an OpenAI-compatible endpoint for a coding or tool-calling agent, with long context.", "strengths": [ "Prebuilt image on ghcr.io with an immutable tag per commit, built by CI that applies all 60 patches and runs the build-time tests", "Tool calling on by default with the `qwen3_coder` parser and argument schemas enforced (`TOOL_STRICT=parameter`)", "With no API key the server listens on 127.0.0.1 only, and a CI check tests that default", "Five documented setups from 64k to 240k context, with the measured cost of each knob", "Apache-2.0 throughout, with vendored kernels and patches carrying their upstream references" ], "weaknesses": [ "Serves Qwen3.8-27B and checkpoints derived from it only. Other models are on the roadmap", "No tags, releases or changelog. Changes reach users through `latest` on every push to main", "No SECURITY.md or disclosure route, and the base weights come from a third-party repository with no pinned revision", "vLLM's key covers only `/v1`-style prefixes, so control routes such as `/pause` answer without it", "First start pulls a 9.5 GB image and about 20 GB of weights and can take over 30 minutes" ], "agentNotes": [ "Call http://127.0.0.1:18020/v1 with model `qwen3.8-27b` and the `VLLM_API_KEY` value, or any string if no key was set", "Poll `/health` before the first request. A first start downloads and prepares the model and compiles kernels, which can take over 30 minutes", "Declare the context window your setup uses (65,536 by default, 131,072 for `CTX=long`, 245,760 for `CTX=huge`) so the client doesn't truncate", "Ask the owner to set `VLLM_API_KEY` before setting `BIND=0.0.0.0`, and to front the port with a proxy that allowlists routes", "Treat the README's tokens-per-second figures as the project's measurements on one RTX 3090 at 250 W" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 56.9 } ], "editorialScores": { "ergonomics": 65, "maintenance": 68, "payments": 60, "reliability": 59, "schema": 56, "security": 41, "transparency": 60 }, "provenanceScore": 49, "checked": { "categories": { "ergonomics": "2026-10-30", "maintenance": "2026-10-30", "payments": "2026-10-30", "reliability": "2026-10-30", "schema": "2026-10-30", "security": "2026-10-30", "transparency": "2026-10-30" }, "last": "2026-10-30", "oldest": "2026-10-30", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "git clone https://github.com/syv-ai/HyperQwen \u0026\u0026 cd HyperQwen\ncp .env.example .env\n\ndocker compose --profile single up -d # one or a few people chatting\ndocker compose --profile batch up -d # API backend, many concurrent requests" }, "letme": { "capability": "https://letme.dev/inference.local", "tool": "https://letme.dev/hyperqwen" }, "area": "models", "provenance": { "legalEntity": "syv.ai (Copenhagen, CVR DK44671247)", "domain": "syv.ai", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "", "privacy": "https://syv.ai/privatlivspolitik", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-10-30", "notes": [ "The Hugging Face organisation syvai, full name syv.ai, links https://syv.ai and github.com/syv-ai, and hosts the drafter files HyperQwen downloads. syv.ai's own pages don't mention HyperQwen.", "syv.ai's contact page gives the address in Copenhagen and CVR DK44671247. The Danish CVR register answered with a bot check and wasn't read.", "No terms, SECURITY.md or changelog for HyperQwen. The Apache-2.0 licence stands in for terms. The privacy policy listed is syv.ai's website policy and doesn't cover the software, which runs on the owner's machine.", "syv.ai answers 404 at /.well-known/security.txt and /security.txt." ], "score": 49 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/hyperqwen.json" }, "facts": [ { "a": "HTTP API", "b": "HTTP API", "name": "Kind" }, { "a": "Docker, Inc.", "b": "syv.ai (syv-ai on GitHub)", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "HTTP", "name": "Transports" }, { "a": "None", "b": "None", "name": "Auth" }, { "a": "Free", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache-2.0 (server, CLI plugin and `dmr` binary). Docker Desktop, which bundles it, is closed software under Docker's subscription agreement, and each model carries its own licence", "b": "Apache-2.0", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "no", "name": "llms.txt" }, { "a": "2026-08-12", "b": "none", "name": "Last release" }, { "a": "2026-08-26", "b": "no document linked", "name": "Terms last updated" }, { "a": "2026-08-26", "b": "no date given", "name": "Privacy policy last updated" }, { "a": "not found in the text", "b": "", "name": "Customer content may train models" }, { "a": "yes", "b": "", "name": "Terms restrict automated access" }, { "a": "yes", "b": "", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "", "name": "Terms or service can change without notice" }, { "a": "yes", "b": "", "name": "Arbitration or class-action waiver" }, { "a": "656 stars", "b": "2.4k stars", "name": "Popularity" } ], "faq": [ { "answer": "Docker Model Runner and HyperQwen score within a point of each other on agent readiness, 57.2 (C) and 56.9 (C). HyperQwen leads on schema \u0026 documentation, agent ergonomics and maintenance \u0026 community.", "question": "Which is better for AI agents, Docker Model Runner or HyperQwen?" }, { "answer": "Neither needs a key.", "question": "Do Docker Model Runner and HyperQwen need an API key?" }, { "answer": "No hosted endpoint is listed for Docker Model Runner. No hosted endpoint is listed for HyperQwen.", "question": "Can an agent call Docker Model Runner and HyperQwen without installing anything?" }, { "answer": "Yes. Docker Model Runner is open source (Apache-2.0 (server, CLI plugin and `dmr` binary). Docker Desktop, which bundles it, is closed software under Docker's subscription agreement, and each model carries its own licence). HyperQwen is open source (Apache-2.0).", "question": "Are Docker Model Runner and HyperQwen open source?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 85 against 59", "Transparency \u0026 trust, 74 against 55" ], "also": null, "goodFor": "A team that already runs Docker and wants local models served to containers and Compose services through OpenAI-, Anthropic- or Ollama-compatible routes, with models stored as OCI artefacts.", "slug": "docker-model-runner", "watchFor": "No credential on the API. The docs say any client that can reach it, including other containers, can pull, load and run models" }, { "aheadOn": [ "Schema \u0026 documentation, 56 against 49", "Agent ergonomics, 65 against 58", "Maintenance \u0026 community, 68 against 55" ], "also": [ "No incidents deducted, where Docker Model Runner loses 3 points for them" ], "goodFor": "An operator with one 24 GB NVIDIA card who wants Qwen3.8-27B behind an OpenAI-compatible endpoint for a coding or tool-calling agent, with long context.", "slug": "hyperqwen", "watchFor": "Serves Qwen3.8-27B and checkpoints derived from it only. Other models are on the roadmap" } ], "job": { "capability": "inference.local", "name": "Local inference" }, "others": [ { "json": "https://www.anchorterminal.com/compare/anythingllm-vs-docker-model-runner.json", "title": "AnythingLLM vs Docker Model Runner", "url": "https://www.anchorterminal.com/compare/anythingllm-vs-docker-model-runner" }, { "json": "https://www.anchorterminal.com/compare/anythingllm-vs-hyperqwen.json", "title": "AnythingLLM vs HyperQwen", "url": "https://www.anchorterminal.com/compare/anythingllm-vs-hyperqwen" }, { "json": "https://www.anchorterminal.com/compare/berth-vs-docker-model-runner.json", "title": "Berth vs Docker Model Runner", "url": "https://www.anchorterminal.com/compare/berth-vs-docker-model-runner" }, { "json": "https://www.anchorterminal.com/compare/berth-vs-hyperqwen.json", "title": "Berth vs HyperQwen", "url": "https://www.anchorterminal.com/compare/berth-vs-hyperqwen" }, { "json": "https://www.anchorterminal.com/compare/bitrun-vs-docker-model-runner.json", "title": "BitRun vs Docker Model Runner", "url": "https://www.anchorterminal.com/compare/bitrun-vs-docker-model-runner" }, { "json": "https://www.anchorterminal.com/compare/bitrun-vs-hyperqwen.json", "title": "BitRun vs HyperQwen", "url": "https://www.anchorterminal.com/compare/bitrun-vs-hyperqwen" }, { "json": "https://www.anchorterminal.com/compare/docker-model-runner-vs-foundry-local.json", "title": "Docker Model Runner vs Foundry Local", "url": "https://www.anchorterminal.com/compare/docker-model-runner-vs-foundry-local" }, { "json": "https://www.anchorterminal.com/compare/docker-model-runner-vs-ghost-core.json", "title": "Docker Model Runner vs Core", "url": "https://www.anchorterminal.com/compare/docker-model-runner-vs-ghost-core" }, { "json": "https://www.anchorterminal.com/compare/docker-model-runner-vs-gpt4all.json", "title": "Docker Model Runner vs GPT4All", "url": "https://www.anchorterminal.com/compare/docker-model-runner-vs-gpt4all" }, { "json": "https://www.anchorterminal.com/compare/docker-model-runner-vs-jan.json", "title": "Docker Model Runner vs Jan", "url": "https://www.anchorterminal.com/compare/docker-model-runner-vs-jan" }, { "json": "https://www.anchorterminal.com/compare/docker-model-runner-vs-khoj.json", "title": "Docker Model Runner vs Khoj", "url": "https://www.anchorterminal.com/compare/docker-model-runner-vs-khoj" }, { "json": "https://www.anchorterminal.com/compare/docker-model-runner-vs-koboldcpp.json", "title": "Docker Model Runner vs KoboldCpp", "url": "https://www.anchorterminal.com/compare/docker-model-runner-vs-koboldcpp" }, { "json": "https://www.anchorterminal.com/compare/docker-model-runner-vs-lemonade.json", "title": "Docker Model Runner vs Lemonade", "url": "https://www.anchorterminal.com/compare/docker-model-runner-vs-lemonade" }, { "json": "https://www.anchorterminal.com/compare/docker-model-runner-vs-llama-cpp.json", "title": "Docker Model Runner vs llama.cpp", "url": "https://www.anchorterminal.com/compare/docker-model-runner-vs-llama-cpp" }, { "json": "https://www.anchorterminal.com/compare/docker-model-runner-vs-lm-studio.json", "title": "Docker Model Runner vs LM Studio", "url": "https://www.anchorterminal.com/compare/docker-model-runner-vs-lm-studio" }, { "json": "https://www.anchorterminal.com/compare/docker-model-runner-vs-localai.json", "title": "Docker Model Runner vs LocalAI", "url": "https://www.anchorterminal.com/compare/docker-model-runner-vs-localai" }, { "json": "https://www.anchorterminal.com/compare/docker-model-runner-vs-mlx-lm.json", "title": "Docker Model Runner vs MLX LM", "url": "https://www.anchorterminal.com/compare/docker-model-runner-vs-mlx-lm" }, { "json": "https://www.anchorterminal.com/compare/docker-model-runner-vs-ollama.json", "title": "Docker Model Runner vs Ollama", "url": "https://www.anchorterminal.com/compare/docker-model-runner-vs-ollama" }, { "json": "https://www.anchorterminal.com/compare/docker-model-runner-vs-open-webui.json", "title": "Docker Model Runner vs Open WebUI", "url": "https://www.anchorterminal.com/compare/docker-model-runner-vs-open-webui" }, { "json": "https://www.anchorterminal.com/compare/docker-model-runner-vs-screenpipe.json", "title": "Docker Model Runner vs screenpipe", "url": "https://www.anchorterminal.com/compare/docker-model-runner-vs-screenpipe" }, { "json": "https://www.anchorterminal.com/compare/docker-model-runner-vs-text-generation-webui.json", "title": "Docker Model Runner vs TextGen", "url": "https://www.anchorterminal.com/compare/docker-model-runner-vs-text-generation-webui" }, { "json": "https://www.anchorterminal.com/compare/docker-model-runner-vs-vllm.json", "title": "Docker Model Runner vs vLLM", "url": "https://www.anchorterminal.com/compare/docker-model-runner-vs-vllm" }, { "json": "https://www.anchorterminal.com/compare/foundry-local-vs-hyperqwen.json", "title": "Foundry Local vs HyperQwen", "url": "https://www.anchorterminal.com/compare/foundry-local-vs-hyperqwen" }, { "json": "https://www.anchorterminal.com/compare/ghost-core-vs-hyperqwen.json", "title": "Core vs HyperQwen", "url": "https://www.anchorterminal.com/compare/ghost-core-vs-hyperqwen" }, { "json": "https://www.anchorterminal.com/compare/gpt4all-vs-hyperqwen.json", "title": "GPT4All vs HyperQwen", "url": "https://www.anchorterminal.com/compare/gpt4all-vs-hyperqwen" }, { "json": "https://www.anchorterminal.com/compare/hyperqwen-vs-jan.json", "title": "HyperQwen vs Jan", "url": "https://www.anchorterminal.com/compare/hyperqwen-vs-jan" }, { "json": "https://www.anchorterminal.com/compare/hyperqwen-vs-khoj.json", "title": "HyperQwen vs Khoj", "url": "https://www.anchorterminal.com/compare/hyperqwen-vs-khoj" }, { "json": "https://www.anchorterminal.com/compare/hyperqwen-vs-koboldcpp.json", "title": "HyperQwen vs KoboldCpp", "url": "https://www.anchorterminal.com/compare/hyperqwen-vs-koboldcpp" }, { "json": "https://www.anchorterminal.com/compare/hyperqwen-vs-lemonade.json", "title": "HyperQwen vs Lemonade", "url": "https://www.anchorterminal.com/compare/hyperqwen-vs-lemonade" }, { "json": "https://www.anchorterminal.com/compare/hyperqwen-vs-llama-cpp.json", "title": "HyperQwen vs llama.cpp", "url": "https://www.anchorterminal.com/compare/hyperqwen-vs-llama-cpp" }, { "json": "https://www.anchorterminal.com/compare/hyperqwen-vs-lm-studio.json", "title": "HyperQwen vs LM Studio", "url": "https://www.anchorterminal.com/compare/hyperqwen-vs-lm-studio" }, { "json": "https://www.anchorterminal.com/compare/hyperqwen-vs-localai.json", "title": "HyperQwen vs LocalAI", "url": "https://www.anchorterminal.com/compare/hyperqwen-vs-localai" }, { "json": "https://www.anchorterminal.com/compare/hyperqwen-vs-mlx-lm.json", "title": "HyperQwen vs MLX LM", "url": "https://www.anchorterminal.com/compare/hyperqwen-vs-mlx-lm" }, { "json": "https://www.anchorterminal.com/compare/hyperqwen-vs-ollama.json", "title": "HyperQwen vs Ollama", "url": "https://www.anchorterminal.com/compare/hyperqwen-vs-ollama" }, { "json": "https://www.anchorterminal.com/compare/hyperqwen-vs-open-webui.json", "title": "HyperQwen vs Open WebUI", "url": "https://www.anchorterminal.com/compare/hyperqwen-vs-open-webui" }, { "json": "https://www.anchorterminal.com/compare/hyperqwen-vs-screenpipe.json", "title": "HyperQwen vs screenpipe", "url": "https://www.anchorterminal.com/compare/hyperqwen-vs-screenpipe" }, { "json": "https://www.anchorterminal.com/compare/hyperqwen-vs-text-generation-webui.json", "title": "HyperQwen vs TextGen", "url": "https://www.anchorterminal.com/compare/hyperqwen-vs-text-generation-webui" }, { "json": "https://www.anchorterminal.com/compare/hyperqwen-vs-vllm.json", "title": "HyperQwen vs vLLM", "url": "https://www.anchorterminal.com/compare/hyperqwen-vs-vllm" }, { "json": "https://www.anchorterminal.com/compare/docker-model-runner-vs-underdog.json", "title": "Docker Model Runner vs Underdog", "url": "https://www.anchorterminal.com/compare/docker-model-runner-vs-underdog" }, { "json": "https://www.anchorterminal.com/compare/hyperqwen-vs-underdog.json", "title": "HyperQwen vs Underdog", "url": "https://www.anchorterminal.com/compare/hyperqwen-vs-underdog" } ], "scores": [ { "by": 26, "docker-model-runner": 85, "edge": "docker-model-runner", "hyperqwen": 59, "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 7, "docker-model-runner": 49, "edge": "hyperqwen", "hyperqwen": 56, "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 7, "docker-model-runner": 58, "edge": "hyperqwen", "hyperqwen": 65, "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "by": 1, "docker-model-runner": 40, "edge": "hyperqwen", "hyperqwen": 41, "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "by": 0, "docker-model-runner": 60, "edge": "", "hyperqwen": 60, "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 13, "docker-model-runner": 55, "edge": "hyperqwen", "hyperqwen": 68, "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 19, "docker-model-runner": 74, "edge": "docker-model-runner", "hyperqwen": 55, "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Docker Model Runner and HyperQwen score within a point of each other on agent readiness, 57.2 (C) and 56.9 (C). HyperQwen leads on schema \u0026 documentation, agent ergonomics and maintenance \u0026 community. Both do local inference.", "tutorials": [], "verdicts": { "docker-model-runner": "CI passes on the main branch, and Docker has published two security advisories with CVEs and fixed versions for the project. The API takes no credential, so any client or container that reaches it can pull, delete and run models, and the documentation has no OpenAPI file or error reference.", "hyperqwen": "HyperQwen packages a patched vLLM 0.32.0 and requantised Qwen3.8-27B weights into one container with tool calling preset and a loopback bind when no key is set. It runs one model family, its speed figures come from one RTX 3090, and it has no versioned releases, changelog or security policy." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/docker-model-runner-vs-hyperqwen", "json": "https://www.anchorterminal.com/compare/docker-model-runner-vs-hyperqwen.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/docker-model-runner-vs-hyperqwen.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/docker-model-runner-vs-hyperqwen.min.md" }, "markdown": "Docker Model Runner and HyperQwen score within a point of each other on agent readiness, 57.2 (C) and 56.9 (C). HyperQwen leads on schema \u0026 documentation, agent ergonomics and maintenance \u0026 community. Both do local inference.\n\n- Docker Model Runner: grade C, 57.2/100, rank #728 of 1239. Markdown https://www.anchorterminal.com/tools/docker-model-runner.md · JSON https://www.anchorterminal.com/api/v1/tools/docker-model-runner.json\n- HyperQwen: grade C, 56.9/100, rank #738 of 1239. Markdown https://www.anchorterminal.com/tools/hyperqwen.md · JSON https://www.anchorterminal.com/api/v1/tools/hyperqwen.json\n- Best local AI models and assistants: https://www.anchorterminal.com/best/local-ai/index.md\n- All 253 local ai comparisons: https://www.anchorterminal.com/compare/local-ai/index.md\n\n## Which one, for what\n\n### Docker Model Runner (C)\n\nGood for: A team that already runs Docker and wants local models served to containers and Compose services through OpenAI-, Anthropic- or Ollama-compatible routes, with models stored as OCI artefacts.\n\nAhead on:\n- Reliability, 85 against 59\n- Transparency \u0026 trust, 74 against 55\n\nWatch for: No credential on the API. The docs say any client that can reach it, including other containers, can pull, load and run models\n\n### HyperQwen (C)\n\nGood for: An operator with one 24 GB NVIDIA card who wants Qwen3.8-27B behind an OpenAI-compatible endpoint for a coding or tool-calling agent, with long context.\n\nAhead on:\n- Schema \u0026 documentation, 56 against 49\n- Agent ergonomics, 65 against 58\n- Maintenance \u0026 community, 68 against 55\n\nAlso in its favour:\n- No incidents deducted, where Docker Model Runner loses 3 points for them\n\nWatch for: Serves Qwen3.8-27B and checkpoints derived from it only. Other models are on the roadmap\n\n\n## Score by category\n\n| Category | Weight | Docker Model Runner | HyperQwen | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 85 | 59 | Docker Model Runner +26 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 49 | 56 | HyperQwen +7 |\n| Agent ergonomics | 13% (16.2 this run) | 58 | 65 | HyperQwen +7 |\n| Security \u0026 auth | 14% (17.5 this run) | 40 | 41 | HyperQwen +1 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 60 | 60 | even |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 55 | 68 | HyperQwen +13 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 74 | 55 | Docker Model Runner +19 |\n| Negative events | ≤15 | -3 | 0 | |\n| **Total** | | **57.2 · C** | **56.9 · C** | |\n\n## Facts side by side\n\n| Fact | Docker Model Runner | HyperQwen |\n| --- | --- | --- |\n| Kind | HTTP API | HTTP API |\n| Vendor | Docker, Inc. | syv.ai (syv-ai on GitHub) |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | HTTP | HTTP |\n| Auth | None | None |\n| Pricing | Free | Free |\n| x402 | no | no |\n| Licence | Apache-2.0 (server, CLI plugin and `dmr` binary). Docker Desktop, which bundles it, is closed software under Docker's subscription agreement, and each model carries its own licence | Apache-2.0 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | no |\n| Last release | 2026-08-12 | none |\n| Terms last updated | 2026-08-26 | no document linked |\n| Privacy policy last updated | 2026-08-26 | no date given |\n| Customer content may train models | not found in the text | |\n| Terms restrict automated access | yes | |\n| Terms restrict benchmarking | yes | |\n| Terms or service can change without notice | not found in the text | |\n| Arbitration or class-action waiver | yes | |\n| Popularity | 656 stars | 2.4k stars |\n\n## Verdicts\n\n**Docker Model Runner.** CI passes on the main branch, and Docker has published two security advisories with CVEs and fixed versions for the project. The API takes no credential, so any client or container that reaches it can pull, delete and run models, and the documentation has no OpenAPI file or error reference.\n\n**HyperQwen.** HyperQwen packages a patched vLLM 0.32.0 and requantised Qwen3.8-27B weights into one container with tool calling preset and a loopback bind when no key is set. It runs one model family, its speed figures come from one RTX 3090, and it has no versioned releases, changelog or security policy.\n\n## Before you call either\n\n### Docker Model Runner\n\n1. Use base URL `http://localhost:12434/engines/v1` for OpenAI clients and `http://localhost:12434` for Anthropic and Ollama clients. Any API key value is accepted\n2. In Docker Desktop, run `docker desktop enable model-runner --tcp 12434` first. Host-side TCP is off by default\n3. From a container, call `http://model-runner.docker.internal` on Docker Desktop or `http://172.17.0.1:12434` on Docker Engine\n4. Raise the context before agent work with `docker model configure --context-size \u003cn\u003e \u003cmodel\u003e`. The llama.cpp default is 4,096 tokens\n5. Name models with their namespace, such as `ai/smollm2`, and expect plain-text error bodies with a 400, 404, 500 or 503 status\n\n### HyperQwen\n\n1. Call http://127.0.0.1:18020/v1 with model `qwen3.8-27b` and the `VLLM_API_KEY` value, or any string if no key was set\n2. Poll `/health` before the first request. A first start downloads and prepares the model and compiles kernels, which can take over 30 minutes\n3. Declare the context window your setup uses (65,536 by default, 131,072 for `CTX=long`, 245,760 for `CTX=huge`) so the client doesn't truncate\n4. Ask the owner to set `VLLM_API_KEY` before setting `BIND=0.0.0.0`, and to front the port with a proxy that allowlists routes\n5. Treat the README's tokens-per-second figures as the project's measurements on one RTX 3090 at 250 W\n\n## Questions\n\n### Which is better for AI agents, Docker Model Runner or HyperQwen?\n\nDocker Model Runner and HyperQwen score within a point of each other on agent readiness, 57.2 (C) and 56.9 (C). HyperQwen leads on schema \u0026 documentation, agent ergonomics and maintenance \u0026 community.\n\n### Do Docker Model Runner and HyperQwen need an API key?\n\nNeither needs a key.\n\n### Can an agent call Docker Model Runner and HyperQwen without installing anything?\n\nNo hosted endpoint is listed for Docker Model Runner. No hosted endpoint is listed for HyperQwen.\n\n### Are Docker Model Runner and HyperQwen open source?\n\nYes. Docker Model Runner is open source (Apache-2.0 (server, CLI plugin and `dmr` binary). Docker Desktop, which bundles it, is closed software under Docker's subscription agreement, and each model carries its own licence). HyperQwen is open source (Apache-2.0).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/docker-model-runner-vs-hyperqwen.json, and with the fewest tokens: https://www.anchorterminal.com/compare/docker-model-runner-vs-hyperqwen.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"docker-model-runner\", \"b\": \"hyperqwen\"}`. From a terminal: `anchor compare docker-model-runner hyperqwen`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/docker-model-runner.json and https://www.anchorterminal.com/api/v1/tools/hyperqwen.json\n\n## Other comparisons with Docker Model Runner or HyperQwen\n\n- [AnythingLLM vs Docker Model Runner](https://www.anchorterminal.com/compare/anythingllm-vs-docker-model-runner.md)\n- [AnythingLLM vs HyperQwen](https://www.anchorterminal.com/compare/anythingllm-vs-hyperqwen.md)\n- [Berth vs Docker Model Runner](https://www.anchorterminal.com/compare/berth-vs-docker-model-runner.md)\n- [Berth vs HyperQwen](https://www.anchorterminal.com/compare/berth-vs-hyperqwen.md)\n- [BitRun vs Docker Model Runner](https://www.anchorterminal.com/compare/bitrun-vs-docker-model-runner.md)\n- [BitRun vs HyperQwen](https://www.anchorterminal.com/compare/bitrun-vs-hyperqwen.md)\n- [Docker Model Runner vs Foundry Local](https://www.anchorterminal.com/compare/docker-model-runner-vs-foundry-local.md)\n- [Docker Model Runner vs Core](https://www.anchorterminal.com/compare/docker-model-runner-vs-ghost-core.md)\n- [Docker Model Runner vs GPT4All](https://www.anchorterminal.com/compare/docker-model-runner-vs-gpt4all.md)\n- [Docker Model Runner vs Jan](https://www.anchorterminal.com/compare/docker-model-runner-vs-jan.md)\n- [Docker Model Runner vs Khoj](https://www.anchorterminal.com/compare/docker-model-runner-vs-khoj.md)\n- [Docker Model Runner vs KoboldCpp](https://www.anchorterminal.com/compare/docker-model-runner-vs-koboldcpp.md)\n- [Docker Model Runner vs Lemonade](https://www.anchorterminal.com/compare/docker-model-runner-vs-lemonade.md)\n- [Docker Model Runner vs llama.cpp](https://www.anchorterminal.com/compare/docker-model-runner-vs-llama-cpp.md)\n- [Docker Model Runner vs LM Studio](https://www.anchorterminal.com/compare/docker-model-runner-vs-lm-studio.md)\n- [Docker Model Runner vs LocalAI](https://www.anchorterminal.com/compare/docker-model-runner-vs-localai.md)\n- [Docker Model Runner vs MLX LM](https://www.anchorterminal.com/compare/docker-model-runner-vs-mlx-lm.md)\n- [Docker Model Runner vs Ollama](https://www.anchorterminal.com/compare/docker-model-runner-vs-ollama.md)\n- [Docker Model Runner vs Open WebUI](https://www.anchorterminal.com/compare/docker-model-runner-vs-open-webui.md)\n- [Docker Model Runner vs screenpipe](https://www.anchorterminal.com/compare/docker-model-runner-vs-screenpipe.md)\n- [Docker Model Runner vs TextGen](https://www.anchorterminal.com/compare/docker-model-runner-vs-text-generation-webui.md)\n- [Docker Model Runner vs vLLM](https://www.anchorterminal.com/compare/docker-model-runner-vs-vllm.md)\n- [Foundry Local vs HyperQwen](https://www.anchorterminal.com/compare/foundry-local-vs-hyperqwen.md)\n- [Core vs HyperQwen](https://www.anchorterminal.com/compare/ghost-core-vs-hyperqwen.md)\n- [GPT4All vs HyperQwen](https://www.anchorterminal.com/compare/gpt4all-vs-hyperqwen.md)\n- [HyperQwen vs Jan](https://www.anchorterminal.com/compare/hyperqwen-vs-jan.md)\n- [HyperQwen vs Khoj](https://www.anchorterminal.com/compare/hyperqwen-vs-khoj.md)\n- [HyperQwen vs KoboldCpp](https://www.anchorterminal.com/compare/hyperqwen-vs-koboldcpp.md)\n- [HyperQwen vs Lemonade](https://www.anchorterminal.com/compare/hyperqwen-vs-lemonade.md)\n- [HyperQwen vs llama.cpp](https://www.anchorterminal.com/compare/hyperqwen-vs-llama-cpp.md)\n- [HyperQwen vs LM Studio](https://www.anchorterminal.com/compare/hyperqwen-vs-lm-studio.md)\n- [HyperQwen vs LocalAI](https://www.anchorterminal.com/compare/hyperqwen-vs-localai.md)\n- [HyperQwen vs MLX LM](https://www.anchorterminal.com/compare/hyperqwen-vs-mlx-lm.md)\n- [HyperQwen vs Ollama](https://www.anchorterminal.com/compare/hyperqwen-vs-ollama.md)\n- [HyperQwen vs Open WebUI](https://www.anchorterminal.com/compare/hyperqwen-vs-open-webui.md)\n- [HyperQwen vs screenpipe](https://www.anchorterminal.com/compare/hyperqwen-vs-screenpipe.md)\n- [HyperQwen vs TextGen](https://www.anchorterminal.com/compare/hyperqwen-vs-text-generation-webui.md)\n- [HyperQwen vs vLLM](https://www.anchorterminal.com/compare/hyperqwen-vs-vllm.md)\n- [Docker Model Runner vs Underdog](https://www.anchorterminal.com/compare/docker-model-runner-vs-underdog.md)\n- [HyperQwen vs Underdog](https://www.anchorterminal.com/compare/hyperqwen-vs-underdog.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-31", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Docker Model Runner vs HyperQwen", "url": "" } ], "description": "Docker Model Runner and HyperQwen score within a point of each other for local inference, 57.2 and 56.9 out of 100. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Docker Model Runner C 57.2", "HyperQwen C 56.9", "scores" ], "h1": "Docker Model Runner vs HyperQwen", "image": "https://www.anchorterminal.com/assets/og/compare-docker-model-runner-vs-hyperqwen.png", "path": "/compare/docker-model-runner-vs-hyperqwen", "published": "2026-10-01", "section": "tools", "title": "Docker Model Runner vs HyperQwen for AI agents (2026)", "toc": null, "updated": "2026-10-30", "url": "https://www.anchorterminal.com/compare/docker-model-runner-vs-hyperqwen" }, "tokens": { "markdown": 3000, "slim": 680 }, "version": 1 }