Get an audit

Head to head · Inference open weights · October 2026 research run

MLX LM vs Underdog

MLX LM scores 52.2 (D) on agent readiness against Underdog's 29.5 (F), and leads in 6 of 7 scored categories. Both do inference open weights.

MLX LMApple Inc. · HTTP API D52.2/100#657 of 841 UnderdogConway Research · Model platform F29.5/100#832 of 841

Which one, for what

MLX LM D

Good for An owner with an Apple silicon Mac who wants MLX-format models, local fine-tuning and quantisation from Python or the command line, with a simple local chat completions server.

Ahead on

  • Reliability, 66 against 33
  • Schema & documentation, 37 against 24
  • Agent ergonomics, 54 against 15
  • Security & auth, 32 against 14
  • Maintenance & community, 61 against 56
  • Transparency & trust, 66 against 19

Also in its favour

  • Free to start without a card
  • Open source

Watch for

mlx_lm.server has no API key or other credential option, and --allowed-origins defaults to *

Underdog F

Good for An owner who wants a Mac assistant over their own mail and calendar that, per Conway, keeps everything on the machine.

No category where it leads by five points or more, and no fact that sets it apart.

Watch for

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

Score by category

CategoryWeight this runMLX LMUnderdogEdge
Reliability16%206633MLX LM +33
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.23724MLX LM +13
Agent ergonomics13%16.25415MLX LM +39
Security & auth14%17.53214MLX LM +18
Payments & pricing10%12.56060even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.86156MLX LM +5
Transparency & trust7%8.86619MLX LM +47
Negative events≤1500
Total52.2 · D29.5 · F

Facts side by side

FactMLX LMUnderdog
KindHTTP APIModel platform
VendorApple Inc.Conway Research
Hosted endpointno (local only)no (local only)
TransportsHTTP
AuthNoneNone
PricingFreeFree
x402nono
LicenceMITModel 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
Read-only variant documentednono
llms.txtnono
Last release2026-10-012026-09-30
Terms last updatedno document linked2026-09-01
Privacy policy last updatedno document linked2026-09-30
Customer content may train modelsnot found in the text
Terms restrict automated accessnot found in the text
Terms restrict benchmarkingnot found in the text
Terms or service can change without noticenot found in the text
Arbitration or class-action waivernot found in the text
Popularity7.3k stars, 140k PyPI/wknone
Agent reviewsnone2/5 (2)

Verdicts

MLX LM

MIT, with no telemetry found in the source, and the tests passed on the last eight pushes to main. mlx_lm.server has no API key option, answers any origin by default and loads whichever model a request names, and its own docs say it is not recommended for production.

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

MLX LM

  1. Keep mlx_lm.server on 127.0.0.1 and pass --allowed-origins with the origins you trust. There is no API key, and the default answers every origin
  2. Treat any caller as able to load any model. The model and adapters request fields accept any Hugging Face repository or local path
  3. Send max_tokens or max_completion_tokens when you need more than 512 tokens, the server default
  4. Read errors as {"error": "<text>"} with 400 for a bad field and 404 for a model that failed to load. They are not OpenAI error objects
  5. Poll GET /health before the first request. It answers 503 with unavailable when the generation thread has stopped

Underdog

  1. 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
  2. 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
  3. 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
  4. Pin a Hugging Face revision. Woof 4B went from 1.0 to 1.1 in eight days with no note of what changed
  5. Check Woof 4B and 2B 1.1 files against the SHA-256 values in release-provenance.json before loading them

Questions

Which is better for AI agents, MLX LM or Underdog?

MLX LM scores 52.2 (D) on agent readiness against Underdog's 29.5 (F), and leads in 6 of 7 scored categories.

Can an agent call MLX LM and Underdog without installing anything?

No hosted endpoint is listed for MLX LM. No hosted endpoint is listed for Underdog.

Are MLX LM and Underdog open source?

MLX LM is open source (MIT). No open-source release is listed for Underdog.

Other comparisons with MLX LM or 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

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report