Like 78

Follow

Nanbeige LLM Lab 1.48k

Text Generation

Transformers

Safetensors

English

Chinese

llama

llm

nanbeige

conversational

text-generation-inference

License: apache-2.0

Model card Files Files and versions xet

Community 3

Deploy

Copy to bucket new

Use this model Instructions to use Nanbeige/Nanbeige4.3-33B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

Transformers How to use Nanbeige/Nanbeige4.3-33B with Transformers:

Use a pipeline as a high-level helper

from transformers import pipeline

pipe = pipeline("text-generation", model="Nanbeige/Nanbeige4.3-33B") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)

pip install -U transformers accelerate

Load model directly

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Nanbeige/Nanbeige4.3-33B") model = AutoModelForCausalLM.from_pretrained("Nanbeige/Nanbeige4.3-33B", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks

Google Colab

Kaggle

Local Apps Settings

vLLM How to use Nanbeige/Nanbeige4.3-33B with vLLM:

Install vLLM from pip:

pip install vllm

Start the vLLM server:

vllm serve "Nanbeige/Nanbeige4.3-33B"

Call the server using curl (OpenAI-compatible API):

curl -X POST "http://localhost:8000/v1/chat/completions"
-H "Content-Type: application/json"
--data '{ "model": "Nanbeige/Nanbeige4.3-33B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'

Use Docker

docker model run hf.co/Nanbeige/Nanbeige4.3-33B

SGLang How to use Nanbeige/Nanbeige4.3-33B with SGLang:

Install SGLang from pip:

pip install sglang

Start the SGLang server:

python3 -m sglang.launch_server
--model-path "Nanbeige/Nanbeige4.3-33B"
--host 0.0.0.0
--port 30000

Call the server using curl (OpenAI-compatible API):

curl -X POST "http://localhost:30000/v1/chat/completions"
-H "Content-Type: application/json"
--data '{ "model": "Nanbeige/Nanbeige4.3-33B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'

Use Docker images

docker run --gpus all
--shm-size 32g
-p 30000:30000
-v ~/.cache/huggingface:/root/.cache/huggingface
--env "HF_TOKEN=<secret>"
--ipc=host
lmsysorg/sglang:latest
python3 -m sglang.launch_server
--model-path "Nanbeige/Nanbeige4.3-33B"
--host 0.0.0.0
--port 30000

Call the server using curl (OpenAI-compatible API):

curl -X POST "http://localhost:30000/v1/chat/completions"
-H "Content-Type: application/json"
--data '{ "model": "Nanbeige/Nanbeige4.3-33B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'

Docker Model Runner How to use Nanbeige/Nanbeige4.3-33B with Docker Model Runner:

docker model run hf.co/Nanbeige/Nanbeige4.3-33B

Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

1. Introduction</span>","children":[],"isValid":true,"title":"1. Introduction"},{"id":"2-model-performance","label":"<span id="Model-Performance">2. Model Performance</span>","children":[],"isValid":true,"title":"2. Model Performance"},{"id":"3-quickstart","label":"<span id="Quickstart">3. Quickstart</span>","children":[{"id":"transformers","label":"Transformers","children":[],"isValid":true,"title":"Transformers"},{"id":"sglang","label":"SGLang","children":[],"isValid":true,"title":"SGLang"},{"id":"vllm","label":"vLLM","children":[],"isValid":true,"title":"vLLM"}],"isValid":true,"title":"3. Quickstart"},{"id":"4-contact","label":"<span id="Contact">4. Contact</span>","children":[],"isValid":true,"title":"4. Contact"},{"id":"5-citation","label":"<span id="Citation">5. Citation</span>","children":[],"isValid":true,"title":"5. Citation"}]}"> 1. Introduction

2. Model Performance

3. Quickstart Transformers

SGLang

vLLM

4. Contact

5. Citation

6. Introduction

In Nanbeige4.3, we take a foundational step toward pushing the boundaries of lightweight agents. Our strategy centers on building a high-capacity teacher agent first, which will subsequently anchor the distillation of advanced agentic capabilities into smaller models.

To this end, we first introduce Nanbeige4.3-33B, designed as the flagship teacher model for the Nanbeige4.3 series. Delivering state-of-the-art agentic performance among open models in the ~30B parameter class, Nanbeige4.3-33B excels at complex coding and professional cowork tasks. It not only offers a powerful, cost-effective option for immediate real-world deployment, but also lays the necessary foundation to power our upcoming small model distillation pipeline (e.g., for Nanbeige4.3-3B).

2. Model Performance

We compare Nanbeige4.3-33B with recently released frontier models at around the 30B-parameter scale: Qwen3.8-27B, Muse-Glimmer-30B, and Gemma4-31B. All models are evaluated at their highest thinking effort. For each benchmark, we use the same inference hyperparameters and harness across models.

Nanbeige4.3-33B leads on most of the benchmarks, showing strong performance in both agentic coding and cowork tasks. Beyond its breadth across benchmarks, Nanbeige4.3-33B shows strong performance on agent tasks across a wide range of professions and industries. For example, on JobBench, it outperforms the baseline in most of the 35 occupations evaluated.

3. Quickstart

The tokenizer provides a configurable chat template for reasoning and tool-use scenarios:

The model supports a context length of up to 524,288 tokens (512K).

We recommend adjusting the inference settings according to the target scenario:

You can run the model with Transformers, SGLang, or vLLM:

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = 'Nanbeige/Nanbeige4.3-33B' tokenizer = AutoTokenizer.from_pretrained( model_id, use_fast=False, trust_remote_code=True ) model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype='auto', device_map='auto', trust_remote_code=True )

messages = [{'role': 'user', 'content': 'Which number is bigger, 9.11 or 9.8?'}] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, return_tensors='pt' ).to(model.device) output_ids = model.generate(inputs, max_new_tokens=1024) response = tokenizer.decode(output_ids[0][inputs.shape[-1]:], skip_special_tokens=True) print(response)

SGLang

MODEL_PATH=/path/to/your/Nanbeige4.3-33B python -m sglang.launch_server
--model-path ${MODEL_PATH}
--host 0.0.0.0
--port 8000
--tp-size 4
--mem-fraction-static 0.8
--reasoning-parser qwen3
--tool-call-parser qwen3_coder

vLLM

MODEL_PATH=/path/to/your/Nanbeige4.3-33B vllm serve ${MODEL_PATH}
--host 0.0.0.0
--port 8000
--tensor-parallel-size 4
--gpu-memory-utilization 0.8
--enable-auto-tool-choice
--reasoning-parser qwen3
--tool-call-parser qwen3_coder

4. Contact

If you have any questions, please open an issue in this repository or contact us at nanbeige@kanzhun.com.

We also welcome collaborations to build domain-specific and industry-focused agents, including joint work on data and training.

5. Citation

If you find our model useful or would like to use it in your own work, please cite this Hugging Face project:

@misc{nanbeige43chat2026, title = {Nanbeige4.3-33B}, author = {Nanbeige Team}, year = {2026}, publisher = {Hugging Face}, howpublished = {\url{https://huggingface.co/Nanbeige/Nanbeige4.3-33B}} }

Downloads last month -

","chat_template":"\n\n{%- macro visible_text(content) -%}\n {%- if content is string -%}\n {{- content }}\n {%- elif content is iterable and content is not mapping -%}\n {%- for item in content -%}\n {%- if item is mapping and item.type == 'text' -%}\n {{- item.text }}\n {%- elif item is string -%}\n {{- item }}\n {%- elif item is mapping and item.type in ['image', 'image_url', 'video', 'video_url', 'audio', 'audio_url', 'input_audio'] -%}\n {%- set media_type = item.type | replace('url', '') | replace('input', '') -%}\n {{- "<reminder>You are unable to process this " ~ media_type ~ " because you don't have multi-modal input ability. Try different methods.</reminder>" }}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{- content }}\n {%- endif -%}\n{%- endmacro -%}\n\n\n{%- set tool_call_format = tool_call_format if tool_call_format is defined else 'xml' %}\n{%- if tools %}\n {{- '<|im_start|>system\n' }} \n {%- if messages|length > 0 and messages[0].get('role', '') == 'system' %}\n {{- visible_text(messages[0].content) + '\n\n' }}\n {%- else %} \n {{- '你是一位工具函数调用专家，你会得到一个问题和一组可能的工具函数。根据问题，你需要进行一个或多个函数/工具调用以实现目的，请尽量尝试探索通过工具解决问题。\n如果没有一个函数可以使用，请直接使用自然语言回复用户。\n如果给定的问题缺少函数所需的参数，请使用自然语言进行提问，向用户询问必要信息。\n如果调用结果已经足够回答用户问题，请对历史结果进行总结，使用自然语言回复用户。' }} \n {%- endif %}\n\n {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}\n {%- for tool in tools %}\n {{- "\n" }}\n {{- tool | tojson }}\n {%- endfor %}\n \n {%- if tool_call_format == 'json' %}\n {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n" }}\n {{- '<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n' }}\n {%- else %}\n {{- "\n</tools>\n\nFor each function call, output the function name and arguments within the following XML format:\n" }}\n {{- '<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call><|im_end|>\n' }}\n {%- endif %}\n \n{%- else %}\n {%- if messages|length > 0 and messages[0].get('role', '') == 'system' %}\n {{- '<|im_start|>system\n' + visible_text(messages[0].content) + '<|im_end|>\n' }}\n {%- else %} \n {{- '<|im_start|>system\n你是南北阁，一款由BOSS直聘自主研发并训练的专业大语言模型。<|im_end|>\n' }} \n {%- endif %}\n{%- endif %}\n\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.get('role', '') == "user" and visible_text(message.content) is string and not(visible_text(message.content).startswith('<tool_response>') and visible_text(message.content).endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n\n{%- for message in messages %}\n {%- if visible_text(message.content) is string %}\n {%- set content = visible_text(message.content) %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n \n {%- if message.get('role', '') == "system" %}\n {%- if not loop.first %}\n {{- raise_exception('System message must be at the beginning.') }}\n {%- endif %}\n \n {%- elif message.get('role', '') == "assistant" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\n').rstrip('\n') %}\n {%- end