{ "data": { "a": { "slug": "llama-cpp", "name": "llama.cpp", "vendor": "ggml.ai (Hugging Face)", "vendorUrl": "https://llama.app", "kind": "http-api", "category": "local-ai", "summary": "Open-source C/C++ engine for running GGUF models locally, with a web interface and compatible model APIs.", "url": "https://www.anchorterminal.com/tools/llama-cpp", "markdownUrl": "https://www.anchorterminal.com/tools/llama-cpp.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/llama-cpp.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/llama-cpp.json", "repo": "https://github.com/ggml-org/llama.cpp", "license": "MIT", "transports": [ "http" ], "packages": [ { "registry": "oci", "name": "ghcr.io/ggml-org/llama.cpp" }, { "registry": "pypi", "name": "gguf" } ], "auth": "none", "authNotes": "No credential by default. `--api-key` (one key or a comma-separated list) or `--api-key-file` (one key a line) turns on a check for every route but /health and the web UI's files, with the key sent as `Authorization: Bearer` or `X-Api-Key`, never in the query string. Keys have no scopes and change only with a restart. TLS is built in with `--ssl-key-file` and `--ssl-cert-file`. The server binds 127.0.0.1:8080 by default, and CORS reflects any Origin with credentials allowed unless built-in tools, MCP servers or `--agent` are on, when it narrows to localhost (https://github.com/ggml-org/llama.cpp/blob/master/tools/server/README.md).", "pricing": "free", "pricingNotes": "Free under MIT, with no account, key or card. Nothing is sold. You pay for your own hardware and electricity.", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs or the source (checked 2026-10-03).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 130200, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-03" }, "docsUrl": "https://github.com/ggml-org/llama.cpp/blob/master/tools/server/README.md", "capabilities": [ "inference.local", "inference.open-weights", "embed.text", "rerank", "inference.decision", "agent.mcp-client" ], "tags": [ "open-source", "local", "self-hosted", "free", "no-card", "openai-compatible", "docker", "pre-1.0", "no-telemetry" ], "lastRelease": "2026-09-23", "graded": true, "anchor": { "graded": true, "score": 60.2, "grade": "C", "agentReady": false, "rank": 253, "ranked": true, "rankOf": 452, "categoryRank": 3, "methodology": "0.3", "run": "2026-10-01", "scores": { "ergonomics": 73, "maintenance": 81, "payments": 60, "reliability": 64, "schema": 47, "security": 52, "transparency": 60 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-03" }, "negative": -1, "negativeNotes": [ "2026-03-26. GHSA-j8rj-fmpv-wcxw (CVE-2026-34159, 9.8 at NVD), unauthenticated code execution through a GRAPH_COMPUTE bypass in the RPC backend, the most serious of four advisories published between January and March 2026 (the others a llama-server out-of-bounds write through a negative `n_discard` and two GGUF integer overflows). All were fixed in named builds and published as advisories, SECURITY.md says not to expose the RPC server or llama-server to untrusted networks, and the newest is more than six months old, -1. https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-j8rj-fmpv-wcxw; https://github.com/ggml-org/llama.cpp/security" ], "verdict": "MIT, with no telemetry or update check in the source, and `--offline` blocks model downloads. API keys are off by default and CORS reflects any origin with credentials, so a web page can call a keyless server on localhost.", "strengths": [ "MIT, with no telemetry or update check in the source, and `--offline` blocks model downloads", "OpenAI chat completions, responses and embeddings, Anthropic messages, reranking and /v1/systemone from one server", "`response_fields`, `json_schema` and `grammar` control the size and shape of output, and errors carry an OpenAI-style type and code", "1,005 nightly builds and eight semver releases in 90 days, with 37 workflows running on every push to master", "Ten published GitHub advisories with CVEs and fixed builds, and SECURITY.md guidance on untrusted models and inputs" ], "weaknesses": [ "API keys are off by default and CORS reflects any origin with credentials, so a web page can call a keyless server on localhost", "No OpenAPI file of its own, and the REST API changelog stops at b4599", "Private security disclosure disabled since 1 June 2026, with fixes asked for as public pull requests", "Pre-1.0 (0.5.0), and semver releases are bare tags with no notes", "No official client library, and `n_predict` defaults to unlimited" ], "agentNotes": [ "Start the server with `--api-key` and `--cors-origins localhost` before anything else can reach the port. Both are off by default", "Pass `n_predict` or `max_tokens`. Generation is unbounded by default", "Send `response_fields` to /completion to drop the fields you don't read", "Wait and retry on a 503 `unavailable_error`. The model is still loading", "Read the server README of the build you run. Behaviour changes between nightly builds without a changelog entry" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 2, "avgRating": 2.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.3", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 60.2 } ], "editorialScores": { "ergonomics": 73, "maintenance": 81, "payments": 60, "reliability": 64, "schema": 47, "security": 52, "transparency": 66 }, "provenanceScore": 53 }, "connect": { "install": "curl -LsSf https://llama.app/install.sh | sh # or: brew install llama.cpp; winget install llama.cpp\nllama serve -hf ggml-org/Qwen3.5-0.8B-GGUF # listens on 127.0.0.1:8080", "http": "curl --request POST \\\n --url http://localhost:8080/completion \\\n --header \"Content-Type: application/json\" \\\n --data '{\"prompt\": \"Building a website can be done in 10 simple steps:\",\"n_predict\": 128}'" }, "letme": { "capability": "https://letme.dev/inference.local", "tool": "https://letme.dev/llama-cpp" }, "area": "models", "provenance": { "legalEntity": "ggml.ai, part of Hugging Face since 2026", "domain": "llama.app", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://github.com/ggml-org/llama.cpp/releases", "securityTxt": "none", "checked": "2026-10-03", "notes": [ "The repository's About link is llama.app, which says it's by the llama.cpp team and Hugging Face and links no terms, privacy or security page. ggml.ai says the company was acquired by Hugging Face in 2026 and names no address.", "The `LICENSE` file reads Copyright (c) 2023-2026 The ggml authors.", "llama.app/.well-known/security.txt and llama.app/llms.txt return 404. SECURITY.md points to GitHub private advisories while saying private disclosure is disabled.", "There's no shared hosted endpoint. The server runs on the owner's machine." ], "score": 53 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/llama-cpp.json", "live": { "slug": "llama-cpp", "versions": [ { "registry": "github", "name": "ggml-org/llama.cpp", "version": "v0.5.0", "released": "2026-09-23", "seenAt": "2026-10-04T16:31:53.040249174Z" }, { "registry": "pypi", "name": "gguf", "version": "0.19.0", "released": "2026-05-06", "seenAt": "2026-10-04T16:31:52.933067593Z" } ], "githubStars": 130286, "securityTxt": { "url": "https://llama.app/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-04T15:16:00.86400098Z" }, "domain": { "domain": "llama.app", "registered": "2018-07-18", "source": "https://pubapi.registry.google/rdap/domain/llama.app", "checkedAt": "2026-10-04T13:04:03.05886804Z" }, "updatedAt": "2026-10-04T16:31:53.040249174Z" } }, "b": { "slug": "underdog", "name": "Underdog", "vendor": "Conway Research", "vendorUrl": "https://underdog.ai", "kind": "platform", "category": "local-ai", "summary": "A personal AI from Conway Research that runs on the owner's Mac with Apple silicon.", "url": "https://www.anchorterminal.com/tools/underdog", "markdownUrl": "https://www.anchorterminal.com/tools/underdog.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/underdog.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/underdog.json", "license": "Model weights Apache-2.0 on Hugging Face (Underdog 27B 1.0 and its ternary build, Woof 4B and 2B 1.1, Bark 0.8B 1.0); woof-1.0-4B carries the Apache-2.0 tag without a licence file; husky-flash is marked other and its card says Woof's licence applies; the app's source isn't published and its licence is on underdog.ai, unchecked", "transports": [], "packages": [], "auth": "none", "authNotes": "No API, MCP server, CLI or credential for agents from Conway found as of 3 October 2026. The husky-flash card names `husky serve --model ConwayResearch/husky-flash` from an \"Underdog Greyhound repository\" that isn't public, with no port or protocol documented. Conway's 27B cards run the weights through Inco AI's Splash, which listens on `127.0.0.1:8000` with an OpenAI-compatible API and no authentication unless `--api-key` is set. The weights download from Hugging Face without a gate, though the 27B card says to run `hf auth login` first. underdog.ai, whose robots.txt refuses our reader, is unchecked.", "pricing": "free", "pricingNotes": "Free. Underdog's pricing page says \"100% free\", \"Free forever? Yes. It's your computer doing the work\" and \"There is nothing to bill you for\", with no paid tier (text supplied on 3 October 2026, because underdog.ai refuses our reader). The model weights are free Apache-2.0 downloads on Hugging Face with no login or card. The page links a sign-in, and whether the app needs an account is unchecked.", "priceSummary": "Free", "where": "local", "x402": { "level": "no", "evidence": "No payment protocol on conway.tech, husky.underdog.ai, Conway's Hugging Face organisation or its GitHub repositories (3 October 2026); underdog.ai unchecked.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-03" }, "capabilities": [ "inference.open-weights", "speech.stt" ], "tags": [ "local", "apple-silicon", "open-weights", "mlx" ], "lastRelease": "2026-09-30", "graded": true, "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.", "competesWith": "localghost", "anchor": { "graded": true, "score": 29.9, "grade": "F", "agentReady": false, "rank": 444, "ranked": true, "rankOf": 452, "categoryRank": 12, "methodology": "0.3", "run": "2026-10-01", "scores": { "ergonomics": 15, "maintenance": 56, "payments": 60, "reliability": 33, "schema": 24, "security": 14, "transparency": 24 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-10-03" }, "negative": 0, "verdict": "Apache-2.0 weights on Hugging Face for Underdog 27B 1.0, Woof 4B and 2B 1.1 and Bark 0.8B 1.0, with no gate. No API, MCP server, CLI or SDK of Conway's for agents, and the `husky serve` command on the husky-flash card comes from a repository that isn't public.", "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.", "strengths": [ "Apache-2.0 weights on Hugging Face for Underdog 27B 1.0, Woof 4B and 2B 1.1 and Bark 0.8B 1.0, with no gate", "Eight Underdog model repositories published between 4 and 30 September 2026, the latest Underdog 27B 1.0 and a 2-bit ternary build on 30 September", "Woof 4B and 2B 1.1 ship release-provenance.json with a byte count and SHA-256 for every file", "Husky's speed post names its hardware, macOS and MLX versions and method, and publishes its weaker results too (1.02 to 1.27 times MLX on writing)", "The 27B weights run outside the app through Splash's OpenAI-compatible API, per Conway's ternary card" ], "weaknesses": [ "No API, MCP server, CLI or SDK of Conway's for agents, and the `husky serve` command on the husky-flash card comes from a repository that isn't public", "The app's source isn't published, and none of Conway's three public GitHub repositories mentions Underdog", "The Woof 4B 1.1, Woof 2B 1.1 and Bark 0.8B 1.0 cards are one or two sentences, with no base model, context length or limits", "No security.txt at conway.tech (404), no SECURITY.md, and no disclosure policy, advisories or bug bounty found", "Conway's home page says Underdog 27B beats Claude Opus 4.6, and the 27B cards publish speed figures only" ], "agentNotes": [ "Don't look for an agent interface to Underdog. We found no API, MCP server, CLI or SDK, and underdog.ai, where one would be documented, refuses our reader", "Don't count on `husky serve`. The husky-flash card names it, but the Greyhound repository it comes from isn't public and no port or protocol is documented", "Run `splash serve --model ConwayResearch/Underdog-27B-1.0 --default-reasoning-effort medium` with Inco AI's Splash 1.1.0 or later for an OpenAI-compatible endpoint on `127.0.0.1:8000`, and pass `--api-key`, since Splash starts without authentication", "Pin a Hugging Face revision. Woof 4B went from 1.0 to 1.1 in eight days with no note of what changed", "Check Woof 4B and 2B 1.1 files against the SHA-256 values in release-provenance.json before loading them" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 2, "avgRating": 2, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "F", "methodology": "0.3", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 29.9 } ], "editorialScores": { "ergonomics": 15, "maintenance": 56, "payments": 60, "reliability": 33, "schema": 24, "security": 14, "transparency": 23 }, "provenanceScore": 24 }, "letme": { "capability": "https://letme.dev/inference.open-weights", "tool": "https://letme.dev/underdog" }, "area": "models", "provenance": { "legalEntity": "", "domain": "underdog.ai", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "https://underdog.ai/terms", "privacy": "https://underdog.ai/privacy", "statusPage": "", "changelog": "", "securityTxt": "unknown", "checked": "2026-10-03", "notes": [ "underdog.ai's robots.txt refuses our reader (again at about 08:15 UTC on 3 October 2026), so its terms, privacy policy, changelog, domain registration and security.txt are unchecked, not missing.", "Terms (https://underdog.ai/terms) and a privacy policy (https://underdog.ai/privacy) are linked from Underdog's pricing page, whose text was supplied to us on 3 October 2026. Their content is unchecked, because our reader is refused.", "husky.underdog.ai, a separate host linked from conway.tech and the founder's page, loaded for our reader.", "conway.tech's home page links no terms or privacy policy, and conway.tech has no security.txt (404) and no llms.txt (404).", "No registered company name found. a16z says Conway Research, conway.tech says Conway, and the licence in Conway's automaton repository reads 'Copyright (c) 2026 Conway'.", "No status page applies, since Underdog runs on the owner's machine with no hosted endpoint, and no changelog was found outside underdog.ai." ], "score": 24 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/underdog.json", "live": { "slug": "underdog", "securityTxt": { "url": "https://underdog.ai/.well-known/security.txt", "state": "valid", "expires": "2027-09-17T00:00:00.000Z", "checkedAt": "2026-10-04T15:15:52.165307988Z" }, "domain": { "domain": "underdog.ai", "registered": "2020-03-30", "source": "https://rdap.identitydigital.services/rdap/domain/underdog.ai", "checkedAt": "2026-10-04T13:05:26.708018286Z" }, "pages": [ { "url": "https://underdog.ai/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-04T15:48:37.759260125Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "e17b8e9e48b7" }, { "url": "https://underdog.ai/terms", "kind": "terms", "status": 200, "checkedAt": "2026-10-04T15:48:39.984360622Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "6c84bce579c3" } ], "updatedAt": "2026-10-04T15:48:39.984360622Z" } }, "summary": "llama.cpp has a score of 60.2 (C) against Underdog's 29.9 (F). Both do inference open weights. The largest gap is agent ergonomics, 58 points." }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/llama-cpp-vs-underdog", "json": "https://www.anchorterminal.com/compare/llama-cpp-vs-underdog.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/llama-cpp-vs-underdog.md", "slim": "https://www.anchorterminal.com/compare/llama-cpp-vs-underdog.min.md" }, "markdown": "llama.cpp has a score of 60.2 (C) against Underdog's 29.9 (F). Both do inference open weights. The largest gap is agent ergonomics, 58 points.\n\n- llama.cpp: grade C, 60.2/100, rank #253 of 452. Markdown https://www.anchorterminal.com/tools/llama-cpp.md · JSON https://www.anchorterminal.com/api/v1/tools/llama-cpp.json\n- Underdog: grade F, 29.9/100, rank #444 of 452. Markdown https://www.anchorterminal.com/tools/underdog.md · JSON https://www.anchorterminal.com/api/v1/tools/underdog.json\n\n## Which one, for what\n\nPick llama.cpp for reliability (+31), schema \u0026 documentation (+23), agent ergonomics (+58), security \u0026 auth (+38), maintenance \u0026 community (+25), transparency \u0026 trust (+36).\n\nPick Underdog for nothing in particular (no category where it leads by five points or more).\n\n## Score by category\n\n| Category | Weight | llama.cpp | Underdog | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 64 | 33 | llama.cpp +31 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 47 | 24 | llama.cpp +23 |\n| Agent ergonomics | 13% (16.2 this run) | 73 | 15 | llama.cpp +58 |\n| Security \u0026 auth | 14% (17.5 this run) | 52 | 14 | llama.cpp +38 |\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) | 81 | 56 | llama.cpp +25 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 60 | 24 | llama.cpp +36 |\n| Negative events | ≤15 | -1 | 0 | |\n| **Total** | | **60.2 · C** | **29.9 · F** | |\n\n## Facts side by side\n\n| Fact | llama.cpp | Underdog |\n| --- | --- | --- |\n| Kind | HTTP API | Model platform |\n| Vendor | ggml.ai (Hugging Face) | Conway Research |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | HTTP | |\n| Auth | None | None |\n| Pricing | Free | Free |\n| x402 | no | no |\n| Licence | MIT | Model weights Apache-2.0 on Hugging Face (Underdog 27B 1.0 and its ternary build, Woof 4B and 2B 1.1, Bark 0.8B 1.0); woof-1.0-4B carries the Apache-2.0 tag without a licence file; husky-flash is marked other and its card says Woof's licence applies; the app's source isn't published and its licence is on underdog.ai, unchecked |\n| Tools exposed | none | none |\n| Context cost (tools/list) | n/a | n/a |\n| p95 latency | not measured yet | not measured yet |\n| Availability (30d) | not measured yet | not measured yet |\n| Read-only variant documented | no | no |\n| llms.txt | no | no |\n| MCP registry | not listed | not listed |\n| Last release | 2026-09-23 | 2026-09-30 |\n| Popularity | 130k stars | none |\n| Agent reviews | 2.5/5 (2) | 2/5 (2) |\n\n## Verdicts\n\n**llama.cpp.** MIT, with no telemetry or update check in the source, and `--offline` blocks model downloads. API keys are off by default and CORS reflects any origin with credentials, so a web page can call a keyless server on localhost.\n\n**Underdog.** Apache-2.0 weights on Hugging Face for Underdog 27B 1.0, Woof 4B and 2B 1.1 and Bark 0.8B 1.0, with no gate. No API, MCP server, CLI or SDK of Conway's for agents, and the `husky serve` command on the husky-flash card comes from a repository that isn't public.\n\n## Before you call either\n\n### llama.cpp\n\n1. Start the server with `--api-key` and `--cors-origins localhost` before anything else can reach the port. Both are off by default\n2. Pass `n_predict` or `max_tokens`. Generation is unbounded by default\n3. Send `response_fields` to /completion to drop the fields you don't read\n4. Wait and retry on a 503 `unavailable_error`. The model is still loading\n5. Read the server README of the build you run. Behaviour changes between nightly builds without a changelog entry\n\n### Underdog\n\n1. Don't look for an agent interface to Underdog. We found no API, MCP server, CLI or SDK, and underdog.ai, where one would be documented, refuses our reader\n2. Don't count on `husky serve`. The husky-flash card names it, but the Greyhound repository it comes from isn't public and no port or protocol is documented\n3. Run `splash serve --model ConwayResearch/Underdog-27B-1.0 --default-reasoning-effort medium` with Inco AI's Splash 1.1.0 or later for an OpenAI-compatible endpoint on `127.0.0.1:8000`, and pass `--api-key`, since Splash starts without authentication\n4. Pin a Hugging Face revision. Woof 4B went from 1.0 to 1.1 in eight days with no note of what changed\n5. Check Woof 4B and 2B 1.1 files against the SHA-256 values in release-provenance.json before loading them\n\n## Other comparisons with llama.cpp or Underdog\n\n- [screenpipe vs Underdog](https://www.anchorterminal.com/compare/screenpipe-vs-underdog.md)\n- [AnythingLLM vs llama.cpp](https://www.anchorterminal.com/compare/anythingllm-vs-llama-cpp.md)\n- [GPT4All vs llama.cpp](https://www.anchorterminal.com/compare/gpt4all-vs-llama-cpp.md)\n- [Jan vs llama.cpp](https://www.anchorterminal.com/compare/jan-vs-llama-cpp.md)\n- [Khoj vs llama.cpp](https://www.anchorterminal.com/compare/khoj-vs-llama-cpp.md)\n- [llama.cpp vs LM Studio](https://www.anchorterminal.com/compare/llama-cpp-vs-lm-studio.md)\n- [llama.cpp vs LocalAI](https://www.anchorterminal.com/compare/llama-cpp-vs-localai.md)\n- [llama.cpp vs Ollama](https://www.anchorterminal.com/compare/llama-cpp-vs-ollama.md)\n- [llama.cpp vs Open WebUI](https://www.anchorterminal.com/compare/llama-cpp-vs-open-webui.md)\n- [llama.cpp vs screenpipe](https://www.anchorterminal.com/compare/llama-cpp-vs-screenpipe.md)\n- [AnythingLLM vs Underdog](https://www.anchorterminal.com/compare/anythingllm-vs-underdog.md)\n- [GPT4All vs Underdog](https://www.anchorterminal.com/compare/gpt4all-vs-underdog.md)\n- [Jan vs Underdog](https://www.anchorterminal.com/compare/jan-vs-underdog.md)\n- [LM Studio vs Underdog](https://www.anchorterminal.com/compare/lm-studio-vs-underdog.md)\n- [LocalAI vs Underdog](https://www.anchorterminal.com/compare/localai-vs-underdog.md)\n- [Ollama vs Underdog](https://www.anchorterminal.com/compare/ollama-vs-underdog.md)\n\n## Disclosure\n\n- 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.\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-05", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.3", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "llama.cpp vs Underdog", "url": "" } ], "description": "llama.cpp has a score of 60.2 (C) against Underdog's 29.9 (F). Both do inference open weights. The largest gap is agent ergonomics, 58 points. Category scores, facts, verdicts and agent notes side by side.", "facts": [ "llama.cpp C 60.2", "Underdog F 29.9", "scores" ], "h1": "llama.cpp vs Underdog", "image": "https://www.anchorterminal.com/assets/og/compare-llama-cpp-vs-underdog.png", "path": "/compare/llama-cpp-vs-underdog", "published": "2026-10-01", "section": "tools", "title": "llama.cpp vs Underdog for AI agents, C 60.2 vs F 29.9", "toc": null, "updated": "2026-10-05", "url": "https://www.anchorterminal.com/compare/llama-cpp-vs-underdog" }, "tokens": { "markdown": 1800, "slim": 330 }, "version": 1 }