Open source
manchego-serve: Manchego, offline.
A small HTTP server that serves exactly the policy behind the model card’s numbers, with pinned, hash-verified weights and no outbound connections. On an NVIDIA A10: 81 ms median per question.
News & releases
The latest signals.
Releases, model-card updates, and open-source work, each linked to its public source.
All entries
Model update
Manchego, against the whole field.
The Manchego cards now compare v2.1 with every trained open ~4B decision model that could be run as shipped (28 in all, counting v2.1), and disclose how its training data was designed, audited and selected.
Model update
Manchego, on Apple silicon.
The MLX 8-bit and 4-bit builds of v2.1, with format results on their cards. Eight bits stays within one decision of bf16; four bits costs six of 80 held-out rows, and says so.
Release
Meet Manchego v2.1.
A second training stage on human-written task definitions repairs v2’s overconfidence on unfamiliar tasks. Calibration error on a sealed set of 25 unseen tasks: 0.153 to 0.040.
Release
Manchego v2.
Trained from the base on 491,520 rows with computed labels and original human annotations. It remains available at the tag v2.
Release
Manchego v1, the first release.
The first release of the 4B decision model. It remains available at the tag v1.
Model update
Motor imagery, with a clear contract.
A cue-paced, 14-channel Core ML classifier: 0.784 on unseen users under subject-grouped cross-validation, 210 of 210 decisions preserved in the port.
Model update
EEG representations for Apple platforms.
The pretrained CBraMod backbone as a Core ML embedder, matching PyTorch to a worst relative L2 of 1.3 × 10⁻⁵ on real EEG.
Open source
A numerical fix for Core ML.
Porting ZUNA1.1 surfaced an epsilon-inflation bug in coremltools’ rms_norm conversion, large enough to change outputs by whole percents at fp32. Reported upstream with a proposed fix and regression tests.
Model update
ZUNA1.1, on Apple platforms.
Zyphra’s newer EEG reconstruction model as fp32 Core ML profiles, with a 14-channel default for EPOC X-style headsets.
Dates are repository updates unless a tagged release date is stated. Each entry links to its public source.
Follow the work
Good questions. Measured answers.
New models, their evidence, and the occasional correction. Model cards come first; this site follows.