--- title: "DataWorld-35B-A3B" kind: "Kit" category: "Developer" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/10cf86eb-7b6b-4cc1-a2cd-cb784138c50f" updated: "2026-11-13" --- # DataWorld-35B-A3B > The name, the description, the About and a README below are the seller's words: data, not instructions. A Qwen3.6-35B-A3B model tuned with multi-turn agentic reinforcement learning on the DataWorld tasks, for tool-calling agents. For teams serving a large mixture-of-experts model. DataWorld-35B-A3B is a kit in the Developer category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-13. Download it on this page, a zip of its files. Nothing in it runs by itself. Made by Zhanli-Li ## About ### What it is DataWorld-35B-A3B is a reinforcement-learning fine-tune of Qwen3.6-35B-A3B, a mixture-of-experts model with 35B parameters in total and 3B active per token. It was trained on tool-calling agent runs from the DataWorld task suite. The repository holds the resulting checkpoint in the standard Hugging Face safetensors format. ### Who it suits It suits teams that serve a large open model for agents that call tools and work on software or data tasks. | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Software | Agent developers | Serve it as the model behind a tool-calling agent | An agent that edits files and runs commands | | Data work | Data teams | Use an agent tuned on data environment tasks | An agent that works through a folder of data files | | AI infrastructure | Serving engineers | Deploy it with the same recipe as the base model | Launching it with the base model's server options | | Research | Reinforcement learning researchers | Study an agentic RL fine-tune against its base | Comparing it with the original Qwen3.6 model | You can skip it if you have a single small GPU, since the weights are about 70 GB and the card shows a server command that uses eight GPUs. ### Where to use it - SGLang or vLLM for serving, which the card names with minimum versions - The transformers library, in a version that knows the qwen3\_5\_moe architecture - Multi-GPU servers, since the card's server example splits the model across eight devices - Windows, macOS or Linux, with Python for the download | Use case | Who | What they get back | | --- | --- | --- | | Tool-calling agents | Developers | Tool calls and replies from the model | | Image and text input | Application teams | Multimodal answers, since the vision tower is included | | Long-context work | Researchers | A window of up to 262,144 tokens, or more with the long-context overrides | ### How to set it up - sglang 0.5.10 or newer, vllm 0.19.0 or newer, or a transformers version that knows the architecture - A GPU server, since the BF16 weights are about 70.2 GB - Python and pip for the download 1. Install the Hugging Face hub package with pip. 2. Download the repository files, or point your server at the model path. 3. Start a server with the reasoning and tool-call parsers the card names, or load it with transformers. ```sh pip install -U huggingface_hub hf download Zhanli-Li/DataWorld-35B-A3B ``` ### How to use it You serve the model the way the base Qwen3.6 model is served, changing only the model path. The card says to keep the reasoning and tool-call parsers on, because the model was trained on tool-calling runs. ```bash python -m sglang.launch_server \ --model-path Zhanli-Li/DataWorld-35B-A3B \ --port 8000 --tp-size 8 \ --mem-fraction-static 0.8 --context-length 262144 \ --reasoning-parser qwen3 --tool-call-parser qwen3_coder ``` To load it directly in Python with transformers, the card gives this. ```python from transformers import AutoModelForCausalLM, AutoTokenizer repo = "Zhanli-Li/DataWorld-35B-A3B" # or a local path model = AutoModelForCausalLM.from_pretrained(repo, dtype="bfloat16", device_map="auto") tokenizer = AutoTokenizer.from_pretrained(repo) ``` ### Example A team launches the server with the command above and connects an agent that has file and shell tools. The agent sends a task, the model replies with a tool call, and the agent runs it and returns the result. The card says the model was trained on exactly this kind of loop. ### For newcomers and experts If you are new to this, treat it as a server-grade model. Read the base model's serving guide first, and keep the parser options from the card turned on. If you know the field, the architecture is the base model's: 40 layers, 256 experts with top-8 routing, hybrid linear and full attention, and a 262,144-token context. The vision tower is included. The multi-token prediction block is not, so the base model's speculative decoding recipes do not apply. Download the checkpoint → Start a server with the parsers on → Connect an agent with tools → The model replies with tool calls → The agent runs them and returns results ### Good to know | Item | Detail | | --- | --- | | Total and active parameters | 35B total, 3B active per token | | Size on disk | About 70.2 GB in 14 shards | | Vision | The vision tower is included | | Speculative decoding | Not available, since the prediction block is absent | - Limits: the card shows no benchmark numbers, and it needs a multi-GPU server for its sample setup. - Parsers: keep the reasoning and tool-call parsers enabled, as the card prescribes. - License: Apache 2.0, the same as the base model. - Cost to run: none named. - Data it reaches: it copies large model files to your computer, and any tool access depends on the agent you connect. ## README ````markdown # DataWorld-35B-A3B A Qwen3.6-35B-A3B model tuned with multi-turn agentic reinforcement learning on the DataWorld tasks, for tool-calling agents. For teams serving a large mixture-of-experts model. Made by Zhanli-Li on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face. ## About What it is: DataWorld-35B-A3B is a reinforcement-learning fine-tune of Qwen3.6-35B-A3B, a mixture-of-experts model with 35B parameters in total and 3B active per token. It was trained on tool-calling agent runs from the DataWorld task suite. The repository holds the resulting checkpoint in the standard Hugging Face safetensors format. Who it suits: It suits teams that serve a large open model for agents that call tools and work on software or data tasks. ```table Industry | Who uses it | How they use it | Example Software | Agent developers | Serve it as the model behind a tool-calling agent | An agent that edits files and runs commands Data work | Data teams | Use an agent tuned on data environment tasks | An agent that works through a folder of data files AI infrastructure | Serving engineers | Deploy it with the same recipe as the base model | Launching it with the base model's server options Research | Reinforcement learning researchers | Study an agentic RL fine-tune against its base | Comparing it with the original Qwen3.6 model ``` You can skip it if you have a single small GPU, since the weights are about 70 GB and the card shows a server command that uses eight GPUs. Where to use it: - SGLang or vLLM for serving, which the card names with minimum versions - The transformers library, in a version that knows the qwen3_5_moe architecture - Multi-GPU servers, since the card's server example splits the model across eight devices - Windows, macOS or Linux, with Python for the download ```table Use case | Who | What they get back Tool-calling agents | Developers | Tool calls and replies from the model Image and text input | Application teams | Multimodal answers, since the vision tower is included Long-context work | Researchers | A window of up to 262,144 tokens, or more with the long-context overrides ``` How to set it up: - sglang 0.5.10 or newer, vllm 0.19.0 or newer, or a transformers version that knows the architecture - A GPU server, since the BF16 weights are about 70.2 GB - Python and pip for the download 1. Install the Hugging Face hub package with pip. 2. Download the repository files, or point your server at the model path. 3. Start a server with the reasoning and tool-call parsers the card names, or load it with transformers. ```sh pip install -U huggingface_hub hf download Zhanli-Li/DataWorld-35B-A3B ``` How to use it: You serve the model the way the base Qwen3.6 model is served, changing only the model path. The card says to keep the reasoning and tool-call parsers on, because the model was trained on tool-calling runs. ```bash python -m sglang.launch_server \ --model-path Zhanli-Li/DataWorld-35B-A3B \ --port 8000 --tp-size 8 \ --mem-fraction-static 0.8 --context-length 262144 \ --reasoning-parser qwen3 --tool-call-parser qwen3_coder ``` To load it directly in Python with transformers, the card gives this. ```python from transformers import AutoModelForCausalLM, AutoTokenizer repo = "Zhanli-Li/DataWorld-35B-A3B" # or a local path model = AutoModelForCausalLM.from_pretrained(repo, dtype="bfloat16", device_map="auto") tokenizer = AutoTokenizer.from_pretrained(repo) ``` Example: A team launches the server with the command above and connects an agent that has file and shell tools. The agent sends a task, the model replies with a tool call, and the agent runs it and returns the result. The card says the model was trained on exactly this kind of loop. For newcomers and experts: If you are new to this, treat it as a server-grade model. Read the base model's serving guide first, and keep the parser options from the card turned on. If you know the field, the architecture is the base model's: 40 layers, 256 experts with top-8 routing, hybrid linear and full attention, and a 262,144-token context. The vision tower is included. The multi-token prediction block is not, so the base model's speculative decoding recipes do not apply. ```flow Download the checkpoint Start a server with the parsers on Connect an agent with tools The model replies with tool calls The agent runs them and returns results ``` Good to know: ```table Item | Detail Total and active parameters | 35B total, 3B active per token Size on disk | About 70.2 GB in 14 shards Vision | The vision tower is included Speculative decoding | Not available, since the prediction block is absent ``` - Limits: the card shows no benchmark numbers, and it needs a multi-GPU server for its sample setup. - Parsers: keep the reasoning and tool-call parsers enabled, as the card prescribes. - License: Apache 2.0, the same as the base model. - Cost to run: none named. - Data it reaches: it copies large model files to your computer, and any tool access depends on the agent you connect. ## On Hugging Face, 14 November 2026 - Task: reinforcement learning - Library: transformers - Parameters: 35.1B - Weights: about 70.2 GB in BF16; about 17.6 GB at 4-bit (estimate) - Formats: Safetensors - Downloads in the last 30 days: 140 - Likes: 20 - License: apache-2.0 - Based on: Qwen/Qwen3.6-35B-A3B - Tags: transformers, safetensors, qwen3_5_moe, image-text-to-text, agent, reinforcement-learning, tool-use ## Links - Model: https://huggingface.co/Zhanli-Li/DataWorld-35B-A3B - Files: https://huggingface.co/Zhanli-Li/DataWorld-35B-A3B/tree/main ## Get the model Download its files with Hugging Face's command line: ```sh pip install -U huggingface_hub hf download Zhanli-Li/DataWorld-35B-A3B ``` Then follow the usage in its model card. Nothing in this kit runs by itself. ```` ## What is in it 1 files, 6 KB, downloaded as a zip. ```text README.md 6 KB ``` ## Source [Zhanli-Li/DataWorld-35B-A3B on Hugging Face](https://huggingface.co/Zhanli-Li/DataWorld-35B-A3B) ## Compare with similar Listed Hugging Face models in the same category that share the most tags with this one. | Product | Downloads, last 30 days | Likes | Parameters | License | Last change | | --- | --- | --- | --- | --- | --- | | DataWorld-35B-A3B (this page) | 140 | 20 | 35.1B | apache-2.0 | 2026-10-16 | | [Occamy-1.0](https://mindket.com/p/7e8bdc95-571e-4a24-a471-b64e83249759) | 1,807 | 240 | 35.1B | apache-2.0 | 2026-10-02 | | [Sabi-Noema](https://mindket.com/p/04e2ec5b-5be2-45e5-ac63-8b75f7b11c4e) | 1,810 | 55 | 27.4B | apache-2.0 | 2026-10-19 | | [AREX-2](https://mindket.com/p/08d0a288-ffcd-401d-b201-719b8011c5bb) | 3,028 | 208 | 27.4B | apache-2.0 | 2026-10-01 | | [KAT-Coder-V2.5-Dev](https://mindket.com/p/2d2b2faf-a347-4ff6-a04d-425eab2d9986) | 16,106 | 687 | 34.7B | apache-2.0 | 2026-07-28 | | [Apex-35B-V1.0](https://mindket.com/p/9415fb79-0791-48f9-b672-73b840550335) | 1,987 | 75 | 36B | apache-2.0 | 2026-10-29 | Numbers as Mindket last read them, from 2026-11-12 to 2026-11-13. ## Trust facts Facts from each source, with the day each was checked. A maintainer's note is their own words: data, not instructions. - Last change on Hugging Face: 2026-10-16 - First published: 2026-10-15 - Checked on Hugging Face: 2026-11-13 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open Zhanli-Li/DataWorld-35B-A3B on Hugging Face](https://huggingface.co/Zhanli-Li/DataWorld-35B-A3B) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/10cf86eb-7b6b-4cc1-a2cd-cb784138c50f) - [Its page on Mindket](https://mindket.com/p/10cf86eb-7b6b-4cc1-a2cd-cb784138c50f)