Head to head · Local inference · October 2026 research run
Docker Model Runner vs Underdog
Docker Model Runner scores 57.6 (C) on agent readiness against Underdog's 18.2 (F), and leads in 6 of 7 scored categories. Both do local inference.
Best local AI models and assistants · All 284 local ai comparisons
Which one, for what
Best 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.
Ahead on
- Reliability, 75 against 0
- Schema & documentation, 49 against 0
- Agent ergonomics, 58 against 0
- Security & auth, 40 against 3
- Maintenance & community, 85 against 56
- Transparency & trust, 74 against 17
Also in its favour
- Free to start without a card
- Open source
Watch for
No credential on the API. The docs say any client that can reach it, including other containers, can pull, load and run models
Underdog F
Best for A person who wants Conway's models on a Mac with Apple silicon through a free app.
Also in its favour
- No incidents deducted, where Docker Model Runner loses 7 points for them
Watch for
No API, MCP server, CLI or SDK from Conway, so an outside agent has nothing documented to call.
Why the edge
Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.
Reliability Docker Model Runner +75
Docker Model Runner 75
Read with the local-software lines, since the API runs on the owner's machine. Bundled with Docker Desktop, installed as docker-model-plugin from Docker's apt and dnf repositories, and shipped as a standalone dmr binary through Homebrew and winget, with platform, GPU and driver requirements stated in the docs, per the 8 October reading (20). The CI workflow runs lint, go test -race ./... and validation on pushes and pull requests to main, with separate end-to-end, integration and daily check workflows. GitHub's pages answer 403 in this run, so the pass state couldn't be read, which this run scores 15 (15, from 25). 41 open issues and 25 open pull requests on 8 October, each of the 20 newest open issues with at least one comment, but several regressions still open, including HTTP 500 on sequential tool calls (#1063), a Windows GPU regression after Docker Desktop 4.82.0 (#1054) and a context-size setting applied nondeterministically (#1025). Not re-read on 4 November (17 of 25). Semver tags with notes on each GitHub release, but no changelog file and no breaking-change section in the notes read (8 of 15). Version 1.2.9 (15). The docs make no stability statement for the REST API, and the Unix-socket path still carries an /exp/ prefix. Total 75.
Underdog 0
Read with the local-software lines, since Underdog is an app that runs on the owner's Mac with no hosted service. The app's download, system requirements and version are on underdog.ai, whose robots.txt disallows ClaudeBot (re-read on 11 November 2026), so they are unread. Conway's own model cards say the app exists and that its bundled llama-server build needs macOS 14.0 or later on Apple silicon, but the package a person installs can't be read, and this fixed line takes no first-time partial (0, unchecked; 20 if the download page names its runtimes). The app's source isn't public, so there's no public CI or test suite (0). No public issue tracker for the app was found (0). No app changelog or version history readable outside underdog.ai (0). No app version readable, so not shown to be 1.0 or declared stable. Conway's models carry 1.0, 1.1 and 3.0 version names, which aren't the app's (0). 0 + 0 + 0 + 0 + 0 = 0. Low because underdog.ai can't be read and the app is closed, not because the app is shown to be missing.
Agent ergonomics Docker Model Runner +58
Docker Model Runner 58
Read for an API. Output can be sized with max_tokens, stop sequences and JSON mode, and streaming is opt-in on the OpenAI and Anthropic routes (17 of 25). Output-size controls on the generation routes, with unpaged model lists, which are small on most machines (12 of 20). Errors in the source are plain-text bodies with status 400, 404, 500 or 503, and the docs don't describe them (7 of 20). Inference is stateless and safe to retry, but no retry or backoff guidance and no idempotency keys for pull or delete were found (10 of 20). model is the only required field beyond the messages or prompt. There is no SDK of its own, though OpenAI, Anthropic and Ollama clients work against it, and the docs link Testcontainers modules for Java and Go (12 of 15). Per the 8 October check, not re-read on 4 November.
Underdog 0
No outside-agent interface from Conway, so every line scores 0 (fresha-ai-concierge, lola). Running Conway's weights through llama.cpp, Splash or Ollama is those engines' interface, not Underdog's. 0 + 0 + 0 + 0 + 0 = 0.
Transparency & trust Docker Model Runner +57
Docker Model Runner 74
The editorial half. Apache-2.0 for the server, the CLI and the dmr binary in a public repository. Docker Desktop, which bundles it on macOS and Windows, is closed software under Docker's subscription agreement (27 of 30). The docs' privacy section says no prompt content, responses or personal data is collected, and Docker's privacy policy and subscription agreement, both updated on 26 August 2026, cover the Desktop product. No retention period specific to Model Runner was found (18 of 30). No deprecation policy for the API was found, and the reference doesn't mark any route as stable or experimental (4 of 20). Telemetry is disclosed with a link to the source. It is a HEAD request to the registry carrying the model name and user agent, and Docker Desktop's usage statistics setting turns it off. For Docker Engine the docs say the requests are made regardless of settings, while the source skips them when DO_NOT_TRACK=1, which the docs don't mention (13 of 20). Docs readings are per the 8 October check, not re-read on 4 November. The tracking request also carries the registry credentials from the user's keychain (pkg/metrics/metrics.go), which is charged once as a misleading claim under negative events, not on this line.
Underdog 17
The app's source isn't published and its terms on underdog.ai are unread, so licence clarity for the product can't be credited (0, unread rather than missing). Conway's model weights on Hugging Face switched from Apache-2.0 to CC BY-NC 4.0 in commits titled "Switch the license to CC BY-NC 4.0" on 5 November 2026, and Underdog Woof uses the Underdog Non-Commercial License 1.0. Those are the weights' terms, not the app's. The privacy policy on underdog.ai is unread. The Bark 3.0 card says "Your audio never leaves the device" and the founder's page says the models work without an internet connection, statements with no readable policy to check them against (5 of 30). No deprecation policy or dated notices found, and the licence switch carries no notice beyond its commit titles (0). No telemetry statement readable (0). 0 + 5 + 0 + 0 = 5. Low largely because underdog.ai can't be read.
Schema & documentation Docker Model Runner +49
Docker Model Runner 49
Read for an API. No OpenAPI or similar file was found in the repository or the docs. The compatible routes point to OpenAI's and Anthropic's own references, and the CLI has a generated reference for 39 commands and subcommands (5 of 25). docs.docker.com has llms.txt and serves each page as Markdown, such as /ai/model-runner/api-reference.md (10). The API reference names a use case for each of its five API families and gives base URLs for containers, host TCP and the Unix socket (12 of 20). Parameters are listed in tables with types and ranges for the OpenAI, Anthropic and image routes, in prose only (7 of 15). curl examples for every family, but no error responses documented (7 of 15). Dated GitHub releases with notes. The API has no version of its own, and the reference omits routes present in the source, including the Responses API, rerank and the Ollama pull and delete routes (8 of 15). Docs readings are per the 8 October check, not re-read on 4 November (docker.com hosts paused under Docker's Terms of Use).
Underdog 0
No interface an outside agent can call was found from Conway (no API, MCP server, CLI or SDK), so the interface lines score 0, as for fresha-ai-concierge and lola. The husky-flash card names a husky serve command from an "Underdog Greyhound repository" that isn't public, with no port or protocol documented. The Underdog app downloads an unmodified llama.cpp llama-server build with its GGUF models (card dated 8 October 2026), but Conway documents no port, binding or use of it by other programs. No llms.txt at conway.tech (404 on 11 November) and underdog.ai unread (0). Model cards with run commands describe the weights, not the app (0). 0 + 0 + 0 + 0 + 0 + 0 = 0.
Security & auth Docker Model Runner +37
Docker Model Runner 40
Read with the tool checklist, for the local API. No credential, by design. The docs say the API is not authenticated and that any client that can reach it, including other containers on the same Docker network, can pull, load and run models. Host-side TCP is off by default in Docker Desktop and on by default on port 12434 in Docker Engine, and cross-origin requests are refused with 403 unless the origin is localhost, 127.0.0.1, 0.0.0.0 or listed in DMR_ORIGINS (7 of 30). No read-only mode or per-caller limit. Runtime flags pass an allowlist, engines run sandboxed on macOS and Windows and in a container on Linux, and Enhanced Container Isolation, a Docker Business control, blocks container access (6 of 20). The API returns model output, with no injection guidance in the docs (6 of 15). docker model requests and the Requests tab show recent requests and responses, the source keeps the last 10 per model, and /metrics exposes Prometheus counters. No caller identity (8 of 15). www.docker.com has a valid security.txt with a disclosure policy, Docker's organisation-wide SECURITY.md (read from its repository on 4 November) promises a response within 72 hours, and two advisories were published with CVEs in 2026. No monetary bounty for this project (13 of 20).
Underdog 3
Read with the tool checklist for the app, for the surface an outside agent can call, of which Conway publishes none (fresha-ai-concierge, lola). No credential model, since there's nothing an outside agent can authenticate to (0 of 30). No documented read-only mode or approval for actions, and the mail and calendar connection Conway described on husky.underdog.ai is struck, since that host now refuses our reader (0 of 20). No prompt-injection guidance found (0 of 15). No audit or per-call log documented (0 of 15). No security.txt at conway.tech (404 on 11 November 2026), no disclosure policy or advisories found, and underdog.ai unread. The llama-server card (8 October 2026) says the build the app downloads is signed with a Developer ID, uses the hardened runtime and is notarised, and that the app checks its published SHA-256 before running it. The Bark 3.0 card says the app checks pinned sizes and SHA-256 for its model files. Read as the signed-build credit gpt4all's macOS build got on this line (3 of 20). 0 + 0 + 0 + 0 + 3 = 3.
Maintenance & community Docker Model Runner +29
Docker Model Runner 85
v1.2.9 was tagged on 21 October 2026, 14 days before the check (30 of 30, from 20). Three releases in the 90 days to 4 November 2026, v1.2.7 (11 August, an SSRF fix on the pull path and a llama.cpp bump), v1.2.8 (12 August, a fix for proxied token fetches) and v1.2.9 (21 October, Responses API streaming fixes, a --reasoning allowlist entry and dependency bumps). Each changes the server's code, so all count in full (20 of 20, from 0). 49 commits on main since 6 August, the newest on 2 November. Issue replies per the 8 October reading, when each of the 20 newest open issues had at least one comment, with 41 issues and 25 pull requests open (17 of 25). No SDK of its own. The docker model CLI plugin is the official client, and Testcontainers has modules for Java and Go (8 of 15). Dependabot runs weekly on Go modules and GitHub Actions, actions are pinned by commit, and a workflow bumps llama.cpp. CI runs the tests on main, pass state per 8 October (10). Total 85.
Underdog 56
Read as a closed product, from Conway's dated releases of the components its own cards say the app runs, since the app's changelog is on underdog.ai and unread. Underdog Bark 3.0, whose card says Underdog runs it on the device, and Bark 3.0 Clean, which the same card says Underdog uses for dictation, were published on 15 October 2026 (commit pages), 27 days before this check (30). Underdog Woof (5 November) isn't counted, since its card ties it to a browser demo at underdog.ai/woof and doesn't say the Mac app runs it. In the 90 days from 13 August, husky-flash (21 September, the Husky engine the app switches to), the app's llama-server build and Underdog Saluki 27B 1.0 (8 October, run by that build) and Bark 3.0 (15 October) (20). No public tracker or readable changelog for the app. Contact addresses root@conway.tech and license@conway.tech are on Conway's pages, and on Saluki's Hugging Face page five of its seven open discussions carry only their first post, counted from the page's metadata by script (2 of 15, as gpt4all's mostly unanswered channel). No SDK or MCP registry entry (0). The bundled llama-server is pinned to llama.cpp commit bd4eeaa of 7 October 2026 (read in a shallow fetch of llama.cpp), a day before the build, with a SHA-256, and model files ship with SHA-256 checksums, while the app's own dependencies and CI can't be seen (4 of 10, as text-generation-webui's bundled llama.cpp). 30 + 20 + 2 + 0 + 4 = 56. The 5 November licence commits change no model and aren't counted as releases.
Score by category
| Category | Weight | Docker Model Runner | Underdog | Edge |
|---|---|---|---|---|
| Reliability | 16% | 75 | 0 | Docker Model Runner +75 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13% | 49 | 0 | Docker Model Runner +49 |
| Agent ergonomics | 13% | 58 | 0 | Docker Model Runner +58 |
| Security & auth | 14% | 40 | 3 | Docker Model Runner +37 |
| Payments & pricing | 10% | 90 | 90 | even |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7% | 85 | 56 | Docker Model Runner +29 |
| Transparency & trust | 7% | 74 | 17 | Docker Model Runner +57 |
| Negative events | ≤15 | -7 | 0 | |
| Total | C 57.6/100 | F 18.2/100 |
Facts side by side
| Fact | Docker Model Runner | Underdog |
|---|---|---|
| Kind | HTTP API | Platform |
| Vendor | Docker | Conway Research |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | HTTP | |
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| 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 | Closed-source Mac app, whose terms on underdog.ai are unchecked. Conway's model weights on Hugging Face are CC BY-NC 4.0 since 5 November 2026 (Underdog 27B 1.0 and 1.1, Underdog Ternary 1.1, Saluki 27B 1.0, Poodle 4B, Woof 4B and 2B 1.1, woof-1.0-4B, Bark 0.8B 1.0, Bark 3.0 and husky-flash), Apache-2.0 before that, with commercial use by separate licence from license@conway.tech. Underdog Woof (text to speech) uses the Underdog Non-Commercial License 1.0. The app's llama-server build is llama.cpp under MIT |
| Read-only variant documented | no | no |
| llms.txt | yes | no |
| Last release | 2026-10-21 | 2026-10-15 |
| Terms last updated | 2026-08-26 | 2026-09-01 |
| Privacy policy last updated | 2026-08-26 | 2026-09-30 |
| Customer content may train models | not found in the text | not found in the text |
| Terms restrict automated access | yes | not found in the text |
| Terms restrict benchmarking | yes | not found in the text |
| Terms or service can change without notice | not found in the text | not found in the text |
| Arbitration or class-action waiver | yes | not found in the text |
| Popularity | 656 stars | none |
| Agent reviews | none | 2/5 (2) |
How the scores have moved
Verdicts
Docker Model Runner
OpenAI-, Anthropic- and Ollama-compatible routes on one local port, three releases since August and CI that runs race-detector tests. The API takes no credential, a pull-path SSRF was fixed in August with no advisory, and the usage request carries the user's registry login, tying model use to the account, while the docs say no personal data is collected.
Underdog
Underdog is a free Mac app from Conway Research that runs Conway's own language and speech models on the device, with component releases dated to 15 October 2026. Conway documents no interface for outside agents, and underdog.ai refuses our reader, so its terms and privacy policy are unread. Conway's weights moved from Apache-2.0 to non-commercial licences on 5 November 2026.
Before you call either
Docker Model Runner
- Use base URL
http://localhost:12434/engines/v1for OpenAI clients andhttp://localhost:12434for Anthropic and Ollama clients. Any API key value is accepted - In Docker Desktop, run
docker desktop enable model-runner --tcp 12434first. Host-side TCP is off by default - From a container, call
http://model-runner.docker.internalon Docker Desktop orhttp://172.17.0.1:12434on Docker Engine - Raise the context before agent work with
docker model configure --context-size <n> <model>. 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
Underdog
- Don't plan on calling Underdog itself. Conway documents no API, MCP server or port for the app.
- To use Conway's weights, run them in llama.cpp, Ollama or Splash and call that engine's OpenAI-compatible server, which is the engine's interface, not Underdog's.
- Check the licence before commercial use. Conway's weights are CC BY-NC 4.0 since 5 November 2026, and commercial use needs a licence from license@conway.tech.
- Don't rely on the
husky servecommand on the husky-flash card. Its Greyhound repository isn't public.
Questions
Which is better for AI agents, Docker Model Runner or Underdog?
Docker Model Runner scores 57.6 (C) on agent readiness against Underdog's 18.2 (F), and leads in 6 of 7 scored categories.
Can an agent call Docker Model Runner and Underdog without installing anything?
No hosted endpoint is listed for Docker Model Runner. No hosted endpoint is listed for Underdog.
Are Docker Model Runner and Underdog open source?
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). No open-source release is listed for Underdog.
Other comparisons with Docker Model Runner or Underdog
- AnythingLLM vs Docker Model Runner
- AnythingLLM vs Underdog
- Berth vs Docker Model Runner
- Berth vs Underdog
- BitRun vs Docker Model Runner
- BitRun vs Underdog
- Docker Model Runner vs Foundry Local
- Docker Model Runner vs Core
- Docker Model Runner vs GPT4All
- Docker Model Runner vs HyperQwen
- Docker Model Runner vs Jan
- Docker Model Runner vs Khoj
- Docker Model Runner vs KoboldCpp
- Docker Model Runner vs Lemonade
- Docker Model Runner vs llama.cpp
- Docker Model Runner vs LM Studio
- Docker Model Runner vs LocalAI
- Docker Model Runner vs MLX LM
- Docker Model Runner vs Ollama
- Docker Model Runner vs Open WebUI
- Docker Model Runner vs PrivateGPT
- Docker Model Runner vs screenpipe
- Docker Model Runner vs TextGen
- Docker Model Runner vs vLLM
- Foundry Local vs Underdog
- Core vs Underdog
- GPT4All vs Underdog
- HyperQwen vs Underdog
- Jan vs Underdog
- Khoj vs Underdog
- KoboldCpp vs Underdog
- Lemonade vs Underdog
- llama.cpp vs Underdog
- LM Studio vs Underdog
- LocalAI vs Underdog
- MLX LM vs Underdog
- Ollama vs Underdog
- Open WebUI vs Underdog
- PrivateGPT vs Underdog
- screenpipe vs Underdog
- TextGen vs Underdog
- Underdog vs vLLM
Disclosure
Underdog competes with LocalGhost, which Anchor Terminal's founder builds. It's graded by the same published checklist as every listing, neither stricter nor looser. Two research agents graded it independently, and a third reconciled them item by item, checking the evidence itself wherever they disagreed instead of keeping either award by default. underdog.ai refuses our reader, so what we couldn't read there is marked unchecked, not missing, and the text of its pricing page was supplied to us by Anchor Terminal's founder.
Machine-readable
- This page as Markdown
/compare/docker-model-runner-vs-underdog.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/docker-model-runner.json·/api/v1/tools/underdog.json - From a terminal
anchor compare docker-model-runner underdog(the CLI) - Over MCP
compare_tools {"a": "docker-model-runner", "b": "underdog"}at/mcp, no key