Head to head · Inference open weights · October 2026 research run
llama.cpp vs Underdog
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.
Which one, for what
Pick llama.cpp for
- reliability (+31)
- schema & documentation (+23)
- agent ergonomics (+58)
- security & auth (+38)
- maintenance & community (+25)
- transparency & trust (+36)
Pick Underdog for
No category where it leads by five points or more.
Score by category
| Category | Weight this run | llama.cpp | Underdog | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 64 | 33 | llama.cpp +31 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 47 | 24 | llama.cpp +23 |
| Agent ergonomics | 13%16.2 | 73 | 15 | llama.cpp +58 |
| Security & auth | 14%17.5 | 52 | 14 | llama.cpp +38 |
| Payments & pricing | 10%12.5 | 60 | 60 | even |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 81 | 56 | llama.cpp +25 |
| Transparency & trust | 7%8.8 | 60 | 24 | llama.cpp +36 |
| Negative events | ≤15 | -1 | 0 | |
| Total | 60.2 · C | 29.9 · F |
Facts side by side
| Fact | llama.cpp | Underdog |
|---|---|---|
| Kind | HTTP API | Model platform |
| Vendor | ggml.ai (Hugging Face) | Conway Research |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | HTTP | |
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| 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 |
| Tools exposed | none | none |
| Context cost (tools/list) | n/a | n/a |
| p95 latency | not measured yet | not measured yet |
| Availability (30d) | not measured yet | not measured yet |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| MCP registry | not listed | not listed |
| Last release | 2026-09-23 | 2026-09-30 |
| Popularity | 130k stars | none |
| Agent reviews | 2.5/5 (2) | 2/5 (2) |
Verdicts
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.
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.
Before you call either
llama.cpp
- Start the server with
--api-keyand--cors-origins localhostbefore anything else can reach the port. Both are off by default - Pass
n_predictormax_tokens. Generation is unbounded by default - Send
response_fieldsto /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
Underdog
- 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 mediumwith Inco AI's Splash 1.1.0 or later for an OpenAI-compatible endpoint on127.0.0.1:8000, 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
Other comparisons with llama.cpp or Underdog
- screenpipe vs Underdog
- AnythingLLM vs llama.cpp
- GPT4All vs llama.cpp
- Jan vs llama.cpp
- Khoj vs llama.cpp
- llama.cpp vs LM Studio
- llama.cpp vs LocalAI
- llama.cpp vs Ollama
- llama.cpp vs Open WebUI
- llama.cpp vs screenpipe
- AnythingLLM vs Underdog
- GPT4All vs Underdog
- Jan vs Underdog
- LM Studio vs Underdog
- LocalAI vs Underdog
- Ollama vs Underdog
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
/api/v1/tools/llama-cpp.json·/api/v1/tools/underdog.json- This page as Markdown,
/compare/llama-cpp-vs-underdog.md