---
title: NuExtract3-JANG_6M
canonical_url: "https://www.modelscope.cn/models/OsaurusAI/NuExtract3-JANG_6M"
md_url: "https://www.modelscope.cn/models/OsaurusAI/NuExtract3-JANG_6M.md"
repository: OsaurusAI/NuExtract3-JANG_6M
last_updated: 2026-10-28
license: apache-2.0
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - qwen3_5
architectures:
  - Qwen3_5ForConditionalGeneration
base_model:
  - numind/NuExtract3
base_model_relation: quantized
parameters: 1.5B
tensor_type:
  - BF16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 10
stars: 0
tags:
  - mlx
  - jang
  - jang_6m
  - quantized
  - apple-silicon
  - nuextract
  - information-extraction
  - osaurus
---

# NuExtract3-JANG_6M

> NuExtract3-JANG_6M - OsaurusAI 在 ModelScope 开源的模型。OsaurusAI/NuExtract3-JANG6M

OsaurusAI/NuExtract3-JANG_6M 是 ModelScope 魔搭社区上的 1.5B 参数image-text-to-text模型，采用 apache-2.0 许可，基于 numind/NuExtract3 构建。

- **Repository**: OsaurusAI/NuExtract3-JANG_6M
- **License**: apache-2.0
- **Tasks**: image-text-to-text
- **Parameters**: 1.5B
- **Base model**: numind/NuExtract3
- **Tags**: mlx, jang, jang_6m, quantized, apple-silicon, nuextract, information-extraction, osaurus
- **Downloads**: 10
- **Stars**: 0
- **Last updated**: 2026-10-28

Source: https://www.modelscope.cn/models/OsaurusAI/NuExtract3-JANG_6M

---

<p align="center"><a href="https://osaurus.ai"><img src="./osaurus-x-banner.png" alt="Osaurus AI"></a></p>

# OsaurusAI/NuExtract3-JANG_6M

JANG_6M build of [numind/NuExtract3](https://huggingface.co/numind/NuExtract3) for Apple Silicon:
structured extraction (typed JSON templates), Markdown conversion and document chat over text
and images, with the native MTP draft head kept.

## Bundle

| | |
|---|---|
| On-disk size | 4.39 GiB (one shard), bfloat16 |
| Full attention q/k/v/o | 8-bit affine, group 32, GPTQ |
| Gated-delta in_proj_qkv / in_proj_z / out_proj | 6-bit affine, group 32, GPTQ |
| Gated-delta decay and beta gates (in_proj_a / in_proj_b) | 8-bit, GPTQ |
| MLP gate / up / down | 6-bit affine, group 32, AWQ + GPTQ |
| Tied embedding / lm_head | 8-bit affine, group 32 |
| MTP draft head (`mtp.*`) | 2-D weights 8-bit group 64; norms raw |
| Kept at full precision | vision tower, conv1d kernels, A_log, dt_bias, all norms |
| GPTQ | 248/248 trunk tensors: fixed bf16 storage grid, act-order, full-corpus Hessians, down_proj Hessian rebuilt through the quantized gate/up, best-of-RTN guard |

## Calibration (371,576 tokens)

Prompts are built by NuExtract3's own template (`mode`, `template`, `enable_thinking`) and
completed by the model itself with the card's sampling (0.2, or 0.6 when thinking), so its JSON,
Markdown and reasoning outputs are in calibration. Documents: synthetic invoices, emails,
resumes, contracts, tickets, statements and more; German Wikipedia; technical and security texts;
rendered receipts, tables, charts, notes and app screenshots.

| task | tokens |
|---|---|
| structured extraction from text (typed JSON templates) | 95,346 |
| document questions and summaries | 60,591 |
| template generation | 26,280 |
| image to Markdown | 81,254 |
| document detection | 18,779 |
| structured extraction from images | 57,361 |
| general text | 31,965 |

## Measured against the bf16 source

47 held-out prompts never seen in calibration (7,537 scored answer
positions), plus 23 held-out extraction tasks answered greedily by each build
and compared with bf16's own JSON.

| build | size | KL mean | top-1 | valid JSON | fields matching bf16 |
|---|---|---|---|---|---|
| **this bundle** | 4.39 GiB | 0.00027 | 99.77% | 23/23 | 87.6% |
| same layout, round-to-nearest | 4.39 GiB | 0.00056 | 99.63% | 23/23 | 88.1% |
| uniform 6-bit gs64 (mlx-vlm default recipe) | 3.81 GiB | 0.00095 | 99.54% | 23/23 | 81.5% |
| numind/NuExtract3-mlx-4bits (official) | 2.83 GiB | 0.01118 | 98.24% | 23/23 | 77.5% |

## Use

Pass NuExtract's template variables as chat-template kwargs (`template`, `mode`,
`instructions`, `enable_thinking`). Non-thinking extraction at temperature 0.2; thinking at 0.6.