---
title: d1a-e4b-it-qat-4bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/d1a-e4b-it-qat-4bit"
md_url: "https://www.modelscope.cn/models/mlx-community/d1a-e4b-it-qat-4bit.md"
repository: mlx-community/d1a-e4b-it-qat-4bit
last_updated: 2026-10-28
license: apache-2.0
pipeline_tag: text-classification
tasks:
- text-classification
model_type:
- gemma4
architectures:
- Gemma4ForConditionalGeneration
base_model:
- google/gemma-4-E4B-it-qat-w4a16-ct
base_model_relation: quantized
parameters: 1.3B
tensor_type:
- BF16
- U32
library_name:
- mlx
- safetensors
- pytorch
frameworks:
- pytorch
language:
- en
- ja
downloads: 13
stars: 0
tags:
- d1a
- decision-model
- calibration
- system-one
- gemma4
- chat
- multimodal
- vision
- audio
- video
- pull-requests
- mlx
- apple-silicon
- quantized
- 4-bit
- qat
- on-device
- experimental
---
# d1a-e4b-it-qat-4bit
> d1a-e4b-it-qat-4bit - mlx-community 在 ModelScope 开源的模型。D1A-E4B-it QAT · MLX 4-bit
mlx-community/d1a-e4b-it-qat-4bit 是 ModelScope 魔搭社区上的 1.3B 参数text-classification模型，采用 apache-2.0 许可，基于 google/gemma-4-E4B-it-qat-w4a16-ct 构建。
- **Repository**: mlx-community/d1a-e4b-it-qat-4bit
- **License**: apache-2.0
- **Tasks**: text-classification
- **Parameters**: 1.3B
- **Base model**: google/gemma-4-E4B-it-qat-w4a16-ct
- **Tags**: d1a, decision-model, calibration, system-one, gemma4, chat, multimodal, vision, audio, video, pull-requests, mlx, apple-silicon, quantized, 4-bit, qat, on-device, experimental
- **Downloads**: 13
- **Stars**: 0
- **Last updated**: 2026-10-28
Source: https://www.modelscope.cn/models/mlx-community/d1a-e4b-it-qat-4bit
---
# D1A-E4B-it QAT · MLX 4-bit
This repository mirrors [JohnP1/d1a-e4b-it-qat-mlx-q4](https://huggingface.co/JohnP1/d1a-e4b-it-qat-mlx-q4) (revision `508ba4af`) byte for byte (the same files, checked by LFS sha256); only this card differs.
**What it does:** decisions (`/v1/systemone`), chat (OpenAI-format `/v1/chat/completions`, streaming included), and
**photos, voice clips and video** (`/v1/systemone/media`). One model on Apple Silicon (MLX), 4.4 GB plus 0.9 GB of encoders
(D1A-E4B-it v0.6 in 8-bit: 6.1 GB plus 0.9 GB).
**Scorecard (2026-10-28): level with D1A-E4B-it v0.6 overall,** stronger on PR labels and routing, weaker on one external suite
([below](#scorecard)). Released 2026-10-27 by the owner's decision, before its gates finished; both gates were set before
training and have since run on every D1A suite, the demos and the PR labeler's data.
**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 build sits exactly on Google's quantization-aware-trained int4 weights,** [google/gemma-4-E4B-it-qat-w4a16-ct](https://huggingface.co/google/gemma-4-E4B-it-qat-w4a16-ct)
(revision `6cd26aaa`). All 343 of its int4 linear layers are stored here bit for bit as MLX 4-bit: the same packed words and
scales, dequantization error 0.0. Nothing is re-quantized from bf16. **The D1A adapter was retrained on this exact trunk,** so
the 4-bit model is the model that was trained, not a rounded copy of it.
**Why it was retrained:**
- The QAT weights differ from the bf16 ones the v0.6 adapter was trained on. On E2B, the v0.6 adapter moved onto its QAT trunk
unchanged lost accuracy and changed 9.6% of its clear-cut answers ([D1A-E2B-it QAT](https://huggingface.co/JohnP1/d1a-e2b-it-qat-mlx-q4)).
- D1A-E4B-it v0.6 was trained with PyTorch on an Apple GPU, where a PyTorch bug read Gemma 4's per-layer embeddings as zeros
for every token id from 199,729: every punctuation and digit token, 28.5% of its training tokens
([jonpol01/d1a#353](https://github.com/jonpol01/d1a/issues/353), [pytorch/pytorch#188756](https://github.com/pytorch/pytorch/issues/188756)).
This retrain reads them correctly (d1a with jonpol01/d1a#354).
## Scorecard
**Against D1A-E4B-it v0.6 (MLX 8-bit): level overall,** pooled −0.16 points [−0.88, +0.51] over 21 lines, with no veto
from D1A's release rules. Against v0.6's adapter moved unchanged onto this same QAT trunk: **+1.19 [+0.50, +1.87]**, 6 significant
wins and no significant loss, so the retrain is what makes the 4-bit trunk work.
- **Stronger than v0.6:** PR labels on the test set +1.6, PR severity with the per-class offsets +6.0, PR blast radius +7.2,
routing +1.7 and +1.5.
- **Weaker than v0.6:** the external typesafe suite, **−7.8** (jonpol01/d1a#361). It comes from the 4-bit trunk, not the
retrain: v0.6's own adapter on this trunk loses nearly as much (−6.9). Calibration is looser on transfer-v4 (ECE 0.081 → 0.105). With the
severity offsets on, it catches fewer P1 pull requests (29 of 47 against 39 of 47) at a higher precision (0.30 against 0.22).
- **Speed:** about the same per decision as v0.6 in 8-bit (ratio 1.01, inside D1A's latency limit), at 5.3 GB instead of 7.0 GB.
- **Photos, voice and video:** of the 28 answers to the 14 demo requests, 26 are the same as v0.6's. The two that differ: an
intact parcel in a mailbox read as "in a delivery locker", and a voice clip about a damaged parcel marked urgent.
Every suite, accuracy in %, Δ in points with paired 95% bootstrap intervals (**bold** where the interval excludes 0); measured
with `scripts/quality_gate.py --all-suites` and `scripts/decide.py` on an Apple M1 Max. ECE and the method: [the full
scorecard](https://github.com/jonpol01/d1a/blob/main/docs/reports/2026-10-28-e4b-it-qat-scorecard.md).
| Suite | n | This build | Δ vs D1A-E4B-it v0.6 | Δ vs v0.6's adapter on this trunk |
|---|---|---|---|---|
| devtools-v1 (card) | 1,074 | 74.6 | +0.2 [-1.1, +1.5] | +0.3 [-1.0, +1.6] |
| documents-v1 (card) | 920 | 88.9 | +0.3 [-1.1, +1.7] | +1.1 [-0.2, +2.4] |
| external semif-v1 | 144 | 88.9 | -2.1 [-5.6, +0.7] | -1.4 [-4.9, +2.1] |
| external typesafe-v1 | 102 | 79.4 | **-7.8 [-11.7, -3.6]** | -1.0 [-5.8, +4.3] |
| external wanli-v1 | 256 | 72.3 | -1.6 [-3.9, +0.8] | +0.4 [-2.3, +3.1] |
| external wanli-v2 | 1,002 | 72.1 | -0.5 [-1.9, +0.9] | **+1.6 [+0.1, +3.1]** |
| hard-v1 (card) | 1,083 | 76.8 | +1.2 [-0.4, +2.9] | **+3.4 [+1.7, +5.4]** |
| ja-jglue development | 1,500 | 80.7 | -0.1 [-1.3, +1.1] | +1.0 [-0.2, +2.3] |
| ja-jglue test | 1,500 | 79.7 | +1.2 [+0.0, +2.4] | **+1.7 [+0.4, +3.0]** |
| night2 assertion | 1,020 | 94.1 | +0.9 [-0.3, +2.0] | **+1.7 [+0.7, +2.7]** |
| night2 dates | 900 | 90.0 | -1.2 [-2.7, +0.2] | +0.9 [-0.2, +2.0] |
| night2 unknowable | 525 | 67.2 | +0.6 [-0.8, +1.9] | +0.6 [-1.0, +2.3] |
| pr-labels development | 2,030 | 80.5 | +0.9 [-0.1, +1.9] | **+1.7 [+0.4, +3.0]** |
| pr-labels development-ja | 198 | 78.8 | +3.5 [-0.5, +7.2] | -0.5 [-5.0, +4.1] |
| pr-labels real17 | 51 | 64.7 | -3.9 [-11.8, +3.9] | +0.0 [-7.8, +7.8] |
| pr-labels test | 2,045 | 81.0 | **+1.6 [+0.5, +2.7]** | **+4.4 [+3.0, +5.9]** |
| pr-labels test-ja | 193 | 76.2 | -0.5 [-2.7, +1.6] | +3.1 [-1.0, +7.4] |
| routing factory-development | 640 | 95.2 | **+1.7 [+0.3, +3.0]** | +0.6 [-0.9, +2.2] |
| routing generic-development | 270 | 98.9 | **+1.5 [+0.4, +3.0]** | +1.1 [+0.0, +2.6] |
| routing handlabelled-45 | 45 | 100.0 | +0.0 [+0.0, +0.0] | +0.0 [+0.0, +0.0] |
| transfer-v4 (card) | 656 | 76.1 | -1.2 [-3.4, +0.8] | +0.0 [-1.8, +1.7] |
| decision-v7 (card) | 1,264 | 86.0 | +0.2 [-0.8, +1.3] | +0.7 [-0.2, +1.6] |
| PR severity, with offsets (test) | 953 | 75.3 | **+6.0 [+3.8, +8.3]** | **+8.6 [+6.1, +11.0]** |
| PR blast radius (test) | 139 | 64.0 | **+7.2 [+1.4, +13.7]** | **+7.9 [+0.7, +14.4]** |
| PR labeler replay (recent PRs) | 193 | 72.0 | +1.0 [-4.2, +6.2] | +2.1 [-3.1, +7.2] |
| owner's PR labels | 109 | 71.6 | +0.9 [-4.4, +6.5] | +4.6 [+0.0, +9.3] |
## What's inside
- **The trunk:** Gemma 4 E4B-it QAT, its 343 int4 linear layers exactly as Google trained them (symmetric, groups of 32);
token and per-layer embeddings 4-bit in groups of 64 (QAT fixes only the Linears' groups of 32). 4.4 GB.
- **The D1A adapter, unmerged** (`adapter/`, LoRA rank 16, 133 MB). With the adapter off the model is Gemma 4 E4B-it QAT
itself, so the same weights also chat.
- **The pointer head** (`head.safetensors`).
- **Calibration temperature 1.66** in `d1a_config.json`, fitted on this build's own answers: 3,178 rows from the decision-v7
calibration split and the PR-label development set, the same recipe as v0.6. Expected calibration error 0.069 → 0.016 out
of fold; 90% interval of the temperature 1.59–1.74. Both sets come from corpora the model trained on, which the fit records.
- **`media/`**: Gemma 4's vision and audio encoders from the QAT checkpoint itself (bf16, 0.9 GB).
## Training
D1A-E4B-it v0.6's recipe, continued on the QAT trunk (jonpol01/d1a#341):
- warm start from [JohnP1/d1a-e4b-it](https://huggingface.co/JohnP1/d1a-e4b-it) v0.6;
- one epoch of v0.6's all-skills mix: 23,427 records from 11 sources (PR labels in English and Japanese, blast radius, recent
PRs, hard, devtools, documents, JGLUE, routing, decision-v7);
- the trunk frozen at the QAT checkpoint's values, dequantized exactly (scale × integer in fp32), the embedding tables in bf16
as the checkpoint stores them (`--embedding_dtype bf16`, jonpol01/d1a#355); learning rate 2e-5, batch 8;
- 2,929 steps, 36.2 hours on an Apple M1 Max (MPS).
## Other checks
- **Exactness:** 343 of 343 quantized linear layers identical to the QAT checkpoint (words, scales and biases).
- **Serving** (`d1a.serving.serve`, Apple M1 Max): the 145 playground demo requests (the 14 photo, voice and video requests
included) and 92 PR-labeler states all answered; the example request below answers `billing` (0.40, shipping 0.37); with the
adapter off, chat answers.
## Run it
Needs d1a with jonpol01/d1a#261:
```bash
pip install "d1a[serve,mlx,media] @ git+https://github.com/jonpol01/d1a"
python -m d1a.serving.serve --run JohnP1/d1a-e4b-it-qat-mlx-q4 --port 8009
```
A decision:
```bash
curl -s localhost:8009/v1/systemone -H 'content-type: application/json' -d '{
"state": "Shoes arrived two weeks late and in the wrong size. Also I see two charges on my card.",
"questions": {"team": {"type": "choice", "instructions": "Which team should handle this?",
"criteria": {"returns": null, "shipping": null, "billing": null}}}
}'
```
A photo, voice clip or video: the same request with a `media` field. `type` is `image` (JPEG, PNG, WebP), `audio` (WAV, FLAC
or OGG, up to 30 s) or `video` (MP4, MOV or WebM, up to 32 MB; 16 frames sampled evenly, the sound track not used):
```bash
curl -s localhost:8009/v1/systemone/media -H 'content-type: application/json' -d '{
"media": {"type": "image", "data": "'"$(base64 -i parcel.jpg)"'"},
"questions": {"damaged": {"type": "noul", "instructions": "Is the parcel damaged?"}}
}'
```
Chat (the adapter is switched off for it, so this is Gemma 4 E4B-it QAT itself):
```bash
curl -s localhost:8009/v1/chat/completions -H 'content-type: application/json' -d '{
"messages": [{"role": "user", "content": "Name three things to check when a parcel arrives damaged."}]
}'
```
or in-process: `from d1a import D1A; D1A.load("JohnP1/d1a-e4b-it-qat-mlx-q4").decide(state, questions)`.
## Limits
- **The external typesafe suite: −7.8 points against D1A-E4B-it v0.6** (above, jonpol01/d1a#361). Pin
[JohnP1/d1a-e4b-it-mlx-q8](https://huggingface.co/JohnP1/d1a-e4b-it-mlx-q8) `v0.6` where answers must match v0.6's.
- **Photos, voice and video** are measured on the 14 demo requests only, zero-shot as on every D1A-E4B-it build.
- **``:** the model was trained with id 2 at the start of every record; d1a adds it (`leading_ids: [2]`). An app that
encodes requests itself must prepend it.
- Questions are in English. The documents can be English or Japanese.
- Everything on the [D1A-E4B-it card](https://huggingface.co/JohnP1/d1a-e4b-it) applies: experimental, and agent tool calls go
through D1A's fail-safe thresholds (`d1a.agents.presets.advise`).
## License and data
Apache-2.0. Base model: Gemma 4 by Google (Apache-2.0). Code: [github.com/jonpol01/d1a](https://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.