North ML 1 / 12
Download PDF

Small models that check their work.

An independent lab building compact open models, and the stack that lets them route, search, verify and act.

North ML · October 2026 · north-ml.space

A common kestrel hovering against the sky

Grounded AI is priced for the few.

Frontier APIs

$2–$50

per million output tokens. Closed weights, cloud only, and your data leaves your machine.

Local small models

Cheap, private

but stale knowledge, made-up facts and no tools. Fluent, not reliable.

The gap isn't raw parameters. Small models can't check their work.

Make the system smart, not just the weights.

  1. RouteA 1,538-parameter router decides whether to search and whether to think.
  2. SearchLive web and Wikipedia, reranked with BM25 and embeddings, passages picked per question.
  3. VerifyFiber-1 Pro checks every claim and number against the sources before answering.
  4. ActPython, maths, time, weather and geocoding tools ship with the runtime.

The model is one component. Routing, search, state and tools are the product.

The Flare-1 lineup.

ModelParametersSize (8-bit)What it adds
Ink-1~725M755 MBStarlight Small backbone with the Kestrel base
Fiber-1~1.63B1.76 GBStarlight Pro backbone with the Kestrel base
Fiber-1 Pro~1.63B1.76 GBOnline GRPO plus a neural fact-verification pass
Flare-Preview1M-class–Architecture preview and a published negative result

All Apache-2.0 on Hugging Face.

One file, one Mac mini.

  • Starlight backbone 24 layers: three gated DeltaNet, then one GQA attention, repeated.
  • Fiber trunk a 158M transformer that routes, drafts tokens and holds associative memory.
  • AgentRegisters memory slots whose state survives across calls.
  • Era lossless snapshots and rollback of every state, for speculative decoding.
  • Kestrel runtime MLX, streaming each stage as it happens.
A silver Mac mini
The whole lineup runs on one M4 Mac mini with 16 GB: about 105 tokens a second.

Measured, then published.

BenchmarkInk-1Fiber-1
ARC-Challenge (1,165 q)63.6%73.5%
MMLU (280 q subset)39.3%48.9%
HumanEval (164)18.3%37.2%
GSM8K (300 q)40.3%unstable, flagged

19/20

Fiber-1 Pro on a held-out reliability eval (Fiber-1 and Ink-1: 17/20), with fictional entities and offline sources.

We publish failures too: Flare-1M showed no significant advantage over a matched GPT baseline, and we said so. English only; no claim of frontier parity.

Thirteen months on Hugging Face.

55public model repos
36.8kmodel downloads, all time
4.2kdownloads in the last 30 days
Sep 2025first upload

All-time downloads of the models released in each month, North-ML1 and arthu1 accounts. Source: Hugging Face API, 21 October 2026.

Shipping, every month.

  1. First uploadssnowy, Neura-1, then astrocoder-star
  2. starlight-minifirst North-ML1 release
  3. North Star familytrained from scratch on one Mac mini
  4. Wind-Edge 1.6 GGUF3.8k downloads; starlight-mini GGUF 4.3k
  5. Willow, Forge-1, Curriculum11 releases in a month
  6. Aurora One Mini3.2k downloads, 6 likes
  7. Qwen3.8-Smol-uo, Aurora Proelia11.4k downloads for Smol-uo
  8. Starlight, then Flare-1Ink-1, Fiber-1, Fiber-1 Pro

What people can use today.

Parallax

A research workspace: plans, searches the live web, cites sources. Ink 1, Fiber 1 Lite, Fiber 1 Pro and Mix.

API

OpenAI-compatible and streaming, with a dashboard, keys and usage logs. One model, north-auto.

Solace

An autonomous coding app that runs its own code and repairs it until tests pass.

Open weights

Every model Apache-2.0, many as GGUF. Download, run, fine-tune.

Accounts are approved by hand during the beta.

What's next.

Known limits, published

  • English only
  • Hallucination is still possible
  • The router is a linear probe
  • One Mac mini serves everything

Plans

  • More inference capacity beyond a single machine
  • Longer-context training to test the Flare mechanisms properly
  • A stronger router, then more languages

Everything we learn, including what fails, gets published.

Run it on your own desk.

Weights on Hugging Face. Papers on the site. An API and a research workspace for anyone we let in.