Hugging Face trending modelspublished Sep 4, 02:55 UTC (12d ago)ingested Sep 17, 01:29 UTCTaichuAI

TaichuAI/ZDTaichu5.0-9B — new model trending #30 on Hugging Face

AI summary · glm-5.3-flash

TaichuAI released ZDTaichu5.0-9B, an open multimodal VLM built on Qwen3.5-9B targeting spatial reasoning, embodied AI, and agentic tool use.

TaichuAI released ZDTaichu5.0-9B, a multimodal vision-language model pairing a Qwen3.5-9B language decoder with a C-RADIOv4-H vision encoder, supporting text, single/multiple images, and video with any-resolution input and a 128K-token context. It introduces Entropy-Gated Adaptive Recurrent Reasoning, which allocates extra latent refinement steps to harder tokens. Reported benchmarks include 87.7 on TAU2-Bench, 71.4 on Claw-Eval, 93.7 on IFEval, 48 on ERQA, and 56 on RoboSpatial, leading compared 10B-scale open VLMs on agent and spatial tasks. The weights are available on Hugging Face, GitHub, and ModelScope, where it is trending at #30.

Pairs a Qwen3.5-9B language backbone with a C-RADIOv4-H vision encoder; accepts text, images, and video.
Leads reported 10B-scale VLM comparisons with TAU2-Bench 87.7, Claw-Eval 71.4, and IFEval 93.7.
Adds Entropy-Gated Adaptive Recurrent Reasoning for adaptive latent-space refinement of difficult tokens.
Targets spatial perception, 3D reasoning, embodied affordances, and multi-step agentic tool use.
Open weights published on Hugging Face, GitHub, and ModelScope; trending #30 at release.

Read the original

VendorsTaichuAI Hugging Face ModelScope

ProductsZDTaichu5.0-9B Qwen3.5-9B C-RADIOv4-H

OrganizationsTaichuAI

AI modelsZDTaichu5.0-9B Qwen3.5-9B

Tagsmultimodal vlm open-weights spatial-reasoning embodied-ai agentic qwen3.5 taichuai

Full article1,687 words · extracted from huggingface.co · click to collapse

# ZDTaichu5.0-9B

[Project Page](https://taichu-ai.github.io/ZDTaichu5.0-9B/) | [GitHub](https://github.com/Taichu-AI/ZDTaichu5.0-9B) | [ModelScope](https://www.modelscope.cn/models/TaichuAI/ZDTaichu5.0-9B)

ZDTaichu5.0-9B is a multimodal foundation model for general visual understanding, spatial reasoning, agentic tool use, and embodied-AI research. It combines a Qwen3.5-9B language backbone with a C-RADIOv4-H vision encoder, supports text, images and videos with any-resolution visual input.

Within the 10B-scale general-purpose VLMs compared in this release blog, ZDTaichu5.0-9B retains first-tier general visual understanding while supporting spatial reasoning, high-level embodied VLM reasoning, and agent tasks under the reported evaluation settings. Rather than trading broad visual competence for specialization, it layers a more comprehensive spatial, embodied, and agent capability profile on top of a strong general-vision foundation.

The model accepts text, one or more images, and video. It is designed for:

- general image, document, chart, diagram, and OCR understanding;

- visual mathematics and knowledge-grounded visual question answering;

- fine-grained 2D relations, multi-view association, 3D scene understanding, perspective taking, and mental transformation;

- multi-step and multi-turn tool use;

- spatial perception, affordance understanding, and planning for VLA and embodied-AI adaptation.

More demos and showcases are provided at [Project Page](https://taichu-ai.github.io/ZDTaichu5.0-9B/).

## Highlights

- **Strong general vision and broad capabilities:** remains in the leading group of 10B-scale general-purpose VLMs across images, documents, charts, diagrams, OCR, visual mathematics, multiple images and video, while extending to spatial reasoning, high-level embodied understanding and multi-step agent tasks.

- **Leading spatial reasoning and embodied understanding:** leads spatial capability among the compared 10B-scale general-purpose VLMs, with strong results on SparBench, ViewSpatial, MMSI-Bench and MindCube-tiny. Scores of 48 on ERQA and 56 on RoboSpatial cover scene reasoning, affordances and interaction-oriented understanding.

- **Strongest agent capability among the compared 10B-scale general-purpose VLMs:** leads the reported TAU2-Bench (87.7) and Claw-Eval (71.4) comparisons, and reaches 93.7 on IFEval.

- **Entropy-Gated Adaptive Recurrent Reasoning:** Dynamically allocates additional recurrent refinement steps in latent space to more challenging tokens, enabling greater computational depth where needed and improving reasoning performance on complex tasks.

## Model Overview

| Item | Specification |

|---|---|

| Model type | Multimodal causal language model with vision encoder |

| Language backbone | Qwen3.5-9B LLM Decoder|

| Vision backbone | C-RADIOv4-H |

| Context length | Up to 128K tokens |

| Vision resolution | Any-resolution visual input |

| Input modalities | Text, single image, multiple images, and video |

## Capabilities

### General visual understanding

The model can recognize objects, attributes, and scenes; read text in natural images and documents; interpret tables, forms, plots, and diagrams; and answer questions that combine visual evidence with language and world knowledge.

### Spatial perception and reasoning

Spatial training covers:

- left/right, above/below, front/behind, occlusion, containment, and relative distance;

- dense counting, fine-grained localization, points, coordinates, and bounding boxes;

- association across images and viewpoints;

- camera motion, relative pose, depth ordering, and room-scale layout;

- egocentric and allocentric perspective taking;

- 2D/3D rotation, paper folding, three-view projection, cross-sections, and part-motion reasoning;

- embodied affordances, manipulation semantics, and high-level action planning.

### Multiple images and video

ZDTaichu5.0-9B compares and reasons across multiple images and supports video understanding, including event tracking and detail retrieval from long footage within its 128K-token context window.

### Agentic tool use

The model is designed for multi-step and multi-turn tool-use tasks. Tool execution must be implemented, validated, and secured by the surrounding application; the model does not execute tools by itself.

## Benchmark Results

The two figures compare ZDTaichu5.0-9B with open and closed models across general visual understanding, spatial and embodied capabilities, and agent and text capabilities.

**Comparison with open models**

![ZDTaichu5.0-9B benchmark comparison with open models](assets/taichu-release-benchmark-comparison.svg)

**Comparison with closed models**

![ZDTaichu5.0-9B benchmark comparison with closed models](assets/taichu-vs-closed-models.svg)

### Spatial and embodied reasoning

<table>

<thead>

<tr>

<th align="left">Benchmark</th>

<th align="right">ZDTaichu5.0-9B</th>

<th align="right">gemma4-8B-E4B</th>

<th align="right">Gemini 3 Pro</th>

</tr>

</thead>

<tbody>

<tr>

<td rowspan="3" align="left" valign="middle">Basic spatial perception</td>

<td align="left">CV-Bench</td>

</tr>

<tr>

<td align="left">3DSRBench</td>

</tr>

<tr>

<td align="left">SparBench</td>

</tr>

<tr>

<td rowspan="3" align="left" valign="middle">Complex spatial reasoning</td>

<td align="left">ViewSpatial</td>

</tr>

<tr>

<td align="left">MMSI-Bench</td>

</tr>

<tr>

<td align="left">MindCube-tiny</td>

Text extracted automatically; images, tables and formatting may be missing. Original: https://huggingface.co/TaichuAI/ZDTaichu5.0-9B