D1A avatar: an anime girl with silver-white and dark purple hair, round glasses and headphones on a round #D1A badge

D1A-E2B-it v0.6 Β· MLX 4-bit (experimental)

A small decision model for Apple Silicon: give it a document and a few questions, and it picks the answers. Each question is yes/no, multiple choice or a score; D1A returns a calibrated probability for every option in one forward pass, with no generated text, so every answer is a valid option.

This is the 4-bit MLX build of JohnP1/d1a-e2b-it v0.6, an experimental build for on-device apps that already load Gemma 4 E2B-it. It is quantized from the same run as the 8-bit build JohnP1/d1a-e2b-it-mlx-q8; no separate training. The iPhone proof of concept it was made for went a different way (2026-10-13, iPhone 17 Pro): D1A ran as an unmerged LoRA adapter on the app's own mlx-community/gemma-4-e2b-it-4bit, rather than as these merged weights.

  • 0 of 42 answers differ from the Mac; 0.52 s per request.
  • The adapter loads in 0.05 s and adds 25 MB.
  • With the adapter off, the model's hidden states are bit-identical to the base, so generation, vision and audio keep base quality.

These merged weights remain the simple route on a Mac, or for an app that does not already hold Gemma.

The -it model is below JohnP1/d1a-e2b v0.6 where it has been measured (severity βˆ’4.3 points on newer PRs, media 21/28 against 25/28 agreement with E4B v0.6, both on the 8-bit build), and E4B v0.6 remains the PR labeler. This 4-bit build has not been scored on any evaluation set. Its only check so far is the Mac comparison below.

Not a chat model. This build has the adapter merged into its weights, so it answers D1A decisions only; text generated from it would come from a changed backbone, not Gemma 4 E2B-it. To chat with the same model that decides, build an unmerged folder from the adapter: see Enable chat.

<bos>: encode with it. The Gemma 4 E2B-it tokenizer adds no <bos>, but this model was trained with one at the start of every record. d1a from jonpol01/d1a#261 on (merged as b4b0f989) puts it back (bos_token_id 2; d1a_config.json records leading_ids: [2]). An app that encodes requests itself must prepend id 2.

What's inside

  • the LoRA adapter merged into Gemma 4 E2B-it (revision 3e22461f); linear layers and token embeddings 4-bit (group 64), per-layer embeddings 4-bit (4.5 bits per weight overall);
  • pointer head fp32 (head.safetensors), the same file as the 8-bit build;
  • calibration temperature 1.41 in d1a_config.json, the run's, not refitted for 4-bit;
  • 2.5 GB on disk for the text model, plus 0.9 GB of photo, voice and video encoders in media/ (the same files as the 8-bit build, unchanged from the -it base).

Mac check on an Apple M1 Max, 28 real requests of up to 512 tokens (42 questions), against the fp32 PyTorch rebuild of the 8-bit export: p50 190 ms, p95 318 ms per request (28 requests), 14 s to load; 4 of 42 answers change (2 of 40 clear-cut ones, where the reference's top answer leads by more than 0.05); largest probability change 0.339.

Results of the 8-bit build (same run)

487 hermes-agent pull requests created after every PR in the training mix, MLX 8-bit at served temperatures, paired 95% bootstrap intervals (details on the 8-bit card):

Question E2B-it v0.6 (8-bit) E2B v0.6 (8-bit) E4B v0.6 E2B-it βˆ’ E2B v0.6
Severity (P0–P4) 72.9% 77.2% 79.1% βˆ’4.3 [βˆ’7.8, βˆ’1.0]
Change type 87.3% 87.5% 90.6% βˆ’0.2 [βˆ’3.1, +2.7]

Photos, voice and video (8-bit build): all 14 demo requests answered; 21 of 28 answers match E4B v0.6 (E2B v0.6: 25 of 28). The card suites (transfer-v4, hard, devtools, documents, decision-v7, JGLUE) are not measured yet on either build.

The bar registered for this run before training (jonpol01/d1a#227, Bar B) failed on severity and media. It is published by the owner's decision of 2026-10-12 for an iOS proof of concept.

Run it

Needs d1a with jonpol01/d1a#261:

pip install "d1a[serve,mlx] @ git+https://github.com/jonpol01/d1a"
python -m d1a.serving.serve --run JohnP1/d1a-e2b-it-mlx-q4@v0.6 --port 8009

or in-process: from d1a import D1A; D1A.load("JohnP1/d1a-e2b-it-mlx-q4@v0.6").decide(state, questions).

Limits

  • Not scored on any evaluation set at 4 bits. Expect it to differ from the 8-bit build's numbers; the Mac check above is the only measurement.
  • Everything on the 8-bit card applies: experimental, below E2B v0.6 on severity and media, not a PR labeller (E4B v0.6 is), most suites not measured, gate tool calls through D1A's fail-safe thresholds (d1a.agents.presets.advise), zero-shot media measured on 14 demo requests.
  • <bos>: requests encoded without the leading id 2 are out of distribution.
  • Questions are in English. The documents can be English or Japanese.

Versions

Tag What it is
v0.6 MLX 4-bit build of D1A-E2B-it v0.6 (experimental)

License and data

Apache-2.0. Base model: Gemma 4 by Google (Apache-2.0). Code: github.com/jonpol01/d1a, built on Kev by Jared Palmer (Apache-2.0). Japanese decision data derived from JGLUE by Yahoo Japan Corporation and Waseda University (CC BY-SA 4.0). Pull-request data from NousResearch/hermes-agent (MIT); the labelled PR dataset itself, including the recent PRs, is private.

Downloads last month
57
Safetensors
Model size
5B params
Tensor type
U32
Β·
BF16
Β·
MLX
Hardware compatibility
Log In to add your hardware

4-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for JohnP1/d1a-e2b-it-mlx-q4

Quantized
(474)
this model

Collection including JohnP1/d1a-e2b-it-mlx-q4