Instructions to use SimplySara/Nanbeige4.1-3B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SimplySara/Nanbeige4.1-3B-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="SimplySara/Nanbeige4.1-3B-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("SimplySara/Nanbeige4.1-3B-GGUF", dtype="auto")

llama-cpp-python

How to use SimplySara/Nanbeige4.1-3B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="SimplySara/Nanbeige4.1-3B-GGUF",
	filename="Nanbeige4.1-3B-BF16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use SimplySara/Nanbeige4.1-3B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf SimplySara/Nanbeige4.1-3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf SimplySara/Nanbeige4.1-3B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf SimplySara/Nanbeige4.1-3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf SimplySara/Nanbeige4.1-3B-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf SimplySara/Nanbeige4.1-3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf SimplySara/Nanbeige4.1-3B-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf SimplySara/Nanbeige4.1-3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf SimplySara/Nanbeige4.1-3B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/SimplySara/Nanbeige4.1-3B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use SimplySara/Nanbeige4.1-3B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SimplySara/Nanbeige4.1-3B-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SimplySara/Nanbeige4.1-3B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SimplySara/Nanbeige4.1-3B-GGUF:Q4_K_M

SGLang

How to use SimplySara/Nanbeige4.1-3B-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "SimplySara/Nanbeige4.1-3B-GGUF" \
    --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": "SimplySara/Nanbeige4.1-3B-GGUF",
		"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 "SimplySara/Nanbeige4.1-3B-GGUF" \
        --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": "SimplySara/Nanbeige4.1-3B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use SimplySara/Nanbeige4.1-3B-GGUF with Ollama:
```
ollama run hf.co/SimplySara/Nanbeige4.1-3B-GGUF:Q4_K_M
```

Unsloth Studio new

How to use SimplySara/Nanbeige4.1-3B-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for SimplySara/Nanbeige4.1-3B-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for SimplySara/Nanbeige4.1-3B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for SimplySara/Nanbeige4.1-3B-GGUF to start chatting

Pi new

How to use SimplySara/Nanbeige4.1-3B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf SimplySara/Nanbeige4.1-3B-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "SimplySara/Nanbeige4.1-3B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use SimplySara/Nanbeige4.1-3B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf SimplySara/Nanbeige4.1-3B-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default SimplySara/Nanbeige4.1-3B-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use SimplySara/Nanbeige4.1-3B-GGUF with Docker Model Runner:
```
docker model run hf.co/SimplySara/Nanbeige4.1-3B-GGUF:Q4_K_M
```

Lemonade

How to use SimplySara/Nanbeige4.1-3B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SimplySara/Nanbeige4.1-3B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Nanbeige4.1-3B-GGUF-Q4_K_M

List all available models

lemonade list

This is a standard quantization of Nanbeige/Nanbeige4.1-3B, made by SimplySara

Model	Size_GB	BPW	PPL_Q	Top_P_Match
`Nanbeige4.1-3B-BF16.gguf`	7.33	16.01	35.5136	100.000%
`Nanbeige4.1-3B-MXFP4_MOE.gguf`	3.9	8.51	35.7776	94.681%
`Nanbeige4.1-3B-i1-MXFP4_MOE.gguf`	3.9	8.51	35.7776	94.681%
`Nanbeige4.1-3B-Q8_0.gguf`	3.9	8.51	35.7776	94.681%
`Nanbeige4.1-3B-i1-Q8_0.gguf`	3.9	8.51	35.7776	94.681%
`Nanbeige4.1-3B-Q6_K.gguf`	3.01	6.57	36.4314	90.241%
`Nanbeige4.1-3B-i1-Q6_K.gguf`	3.01	6.57	35.5096	90.793%
`Nanbeige4.1-3B-Q5_1.gguf`	2.78	6.07	35.8377	82.867%
`Nanbeige4.1-3B-i1-Q5_1.gguf`	2.78	6.07	36.5278	87.097%
`Nanbeige4.1-3B-Q5_K_M.gguf`	2.63	5.75	36.3385	85.444%
`Nanbeige4.1-3B-i1-Q5_K_M.gguf`	2.63	5.75	36.7817	87.277%
`Nanbeige4.1-3B-i1-Q5_0.gguf`	2.58	5.64	35.3274	84.947%
`Nanbeige4.1-3B-Q5_K_S.gguf`	2.58	5.62	36.9553	82.225%
`Nanbeige4.1-3B-i1-Q5_K_S.gguf`	2.58	5.62	36.0077	86.763%
`Nanbeige4.1-3B-Q5_0.gguf`	2.58	5.62	34.471	81.485%
`Nanbeige4.1-3B-i1-Q4_1.gguf`	2.37	5.18	34.9182	80.453%
`Nanbeige4.1-3B-Q4_1.gguf`	2.37	5.18	36.7138	72.166%
`Nanbeige4.1-3B-i1-Q4_K_M.gguf`	2.27	4.97	35.1169	80.951%
`Nanbeige4.1-3B-Q4_K_M.gguf`	2.27	4.97	35.551	76.667%
`Nanbeige4.1-3B-IQ4_NL.gguf`	2.18	4.77	35.462	75.484%
`Nanbeige4.1-3B-Q4_K_S.gguf`	2.18	4.76	36.9027	73.805%
`Nanbeige4.1-3B-i1-Q4_K_S.gguf`	2.18	4.76	35.2205	80.920%
`Nanbeige4.1-3B-i1-Q4_0.gguf`	2.17	4.75	32.071	75.748%
`Nanbeige4.1-3B-i1-IQ4_NL.gguf`	2.17	4.74	33.9382	80.165%
`Nanbeige4.1-3B-Q4_0.gguf`	2.17	4.73	31.1932	72.255%
`Nanbeige4.1-3B-IQ4_XS.gguf`	2.09	4.56	36.4346	76.044%
`Nanbeige4.1-3B-i1-IQ4_XS.gguf`	2.07	4.52	34.318	80.400%
`Nanbeige4.1-3B-Q3_K_L.gguf`	2	4.37	36.5177	70.362%
`Nanbeige4.1-3B-i1-Q3_K_L.gguf`	2	4.37	36.735	73.594%
`Nanbeige4.1-3B-Q3_K_M.gguf`	1.88	4.1	33.7037	67.260%
`Nanbeige4.1-3B-i1-Q3_K_M.gguf`	1.88	4.1	36.8062	72.679%
`Nanbeige4.1-3B-i1-IQ3_M.gguf`	1.78	3.88	35.4695	68.806%
`Nanbeige4.1-3B-IQ3_M.gguf`	1.78	3.88	38.1415	60.134%
`Nanbeige4.1-3B-IQ3_S.gguf`	1.74	3.8	909.214	22.657%
`Nanbeige4.1-3B-i1-IQ3_S.gguf`	1.74	3.8	35.6732	67.415%
`Nanbeige4.1-3B-i1-Q3_K_S.gguf`	1.73	3.78	34.9748	66.103%
`Nanbeige4.1-3B-Q3_K_S.gguf`	1.73	3.78	38.1397	61.667%
`Nanbeige4.1-3B-i1-IQ3_XS.gguf`	1.67	3.65	35.2176	66.490%
`Nanbeige4.1-3B-i1-IQ3_XXS.gguf`	1.55	3.38	33.543	61.474%
`Nanbeige4.1-3B-i1-Q2_K.gguf`	1.51	3.3	38.3969	59.878%
`Nanbeige4.1-3B-Q2_K.gguf`	1.51	3.3	57.987	47.507%
`Nanbeige4.1-3B-i1-Q2_K_S.gguf`	1.43	3.13	44.2038	57.847%
`Nanbeige4.1-3B-i1-IQ2_M.gguf`	1.41	3.08	38.2793	56.770%
`Nanbeige4.1-3B-i1-IQ2_S.gguf`	1.33	2.9	42.7728	52.282%
`Nanbeige4.1-3B-i1-IQ2_XS.gguf`	1.25	2.73	48.201	49.136%
`Nanbeige4.1-3B-i1-IQ2_XXS.gguf`	1.17	2.55	58.2207	44.731%
`Nanbeige4.1-3B-i1-IQ1_M.gguf`	1.07	2.33	110.923	36.721%
`Nanbeige4.1-3B-i1-IQ1_S.gguf`	1.01	2.2	234.974	29.321%

Introduction

Nanbeige4.1-3B is built upon Nanbeige4-3B-Base and represents an enhanced iteration of our previous reasoning model, Nanbeige4-3B-Thinking-2511, achieved through further post-training optimization with supervised fine-tuning (SFT) and reinforcement learning (RL). As a highly competitive open-source model at a small parameter scale, Nanbeige4.1-3B illustrates that compact models can simultaneously achieve robust reasoning, preference alignment, and effective agentic behaviors.

Specifically, Nanbeige4.1-3B exhibits the following key strengths:

Strong Reasoning: Nanbeige4.1-3B is capable of solving complex, multi-step problems through sustained and coherent reasoning within a single forward pass, and reliably produces correct final answers on challenging tasks such as LiveCodeBench-Pro, IMO-Answer-Bench, and AIME 2026 I.
Robust Preference Alignment: Nanbeige4.1-3B achieves solid alignment performance, outperforming not only same-scale models such as Qwen3-4B-2507 and Nanbeige4-3B-2511, but also substantially larger models including Qwen3-30B-A3B and Qwen3-32B on Arena-Hard-v2 and Multi-Challenge.
Agentic Capability: Nanbeige4.1-3B is the first general small model to natively support deep-search tasks and reliably sustain complex problem solving involving more than 500 rounds of tool invocations. It fills a long-standing gap in the small-model ecosystem where models are typically optimized for either general reasoning or agentic scenarios, but rarely excel at both.

Technical Report: Link

Performances

We evaluate Nanbeige4.1-3B across a broad and diverse set of benchmarks covering general reasoning, and deep-search capabilities.

General Reasoning Tasks

On general reasoning tasks including code, math, science, alignment, and tool-use benchmarks, Nanbeige4.1-3B not only significantly outperforms same-scale models such as Qwen3-4B, but also demonstrates overall superior performance compared to larger models including Qwen3-30B-A3B-2507 and Qwen3-32B.

Benchmark	Qwen3-4B-2507	Qwen3-8B	Qwen3-14B	Qwen3-32B	Qwen3-30B-A3B-2507	Nanbeige4-3B-2511	Nanbeige4.1-3B
Code
Live-Code-Bench-V6	57.4	49.4	55.9	55.7	66.0	46.0	76.9
Live-Code-Bench-Pro-Easy	40.2	41.2	33.0	42.3	60.8	40.2	81.4
Live-Code-Bench-Pro-Medium	5.3	3.5	1.8	3.5	3.5	5.3	28.1
Math
AIME 2026 I	81.46	70.42	76.46	75.83	87.30	84.1	87.40
HMMT Nov	68.33	48.33	56.67	57.08	71.25	66.67	77.92
IMO-Answer-Bench	48.00	36.56	41.81	43.94	54.34	38.25	53.38
Science
GPQA	65.8	62.0	63.38	68.4	73.4	82.2	83.8
HLE (Text-only)	6.72	5.28	7.00	9.31	11.77	10.98	12.60
Alignment
Arena-Hard-v2	34.9	26.3	36.9	56.0	60.2	60.0	73.2
Multi-Challenge	41.14	36.30	36.97	38.72	49.40	41.20	52.21
Tool Use
BFCL-V4	44.87	42.20	45.14	47.90	48.6	53.8	56.50
Tau2-Bench	45.9	42.06	44.96	45.26	47.70	41.77	48.57

Deep Search Tasks

As a general small model, Nanbeige4.1-3B achieves deep-search performance comparable to specialized agents under 10B parameters. In contrast to existing small general models, which typically exhibit little to no deep-search capability, Nanbeige4.1-3B represents a substantial qualitative improvement over prior small general models.

Deep Search and Agent Benchmarks

Model	xBench-DeepSearch-2505	xBench-DeepSearch-2510	Browse-Comp	Browse-Comp-ZH	GAIA (Text-only)	HLE	SEAL-0
Search-Specialized Small Agents
MiroThinker-v1.0-8B	61	–	31.1	40.2	66.4	21.5	40.4
AgentCPM-Explore-4B	70	–	25.0	29.0	63.9	19.1	40.0
Large Foundation Models (with Tools)
GLM-4.6-357B	70	–	45.1	49.5	71.9	30.4	–
Minimax-M2-230B	72	–	44.0	48.5	75.7	31.8	–
DeepSeek-V3.2-671B	71	–	67.6	65.0	63.5	40.8	38.5
Small Foundation Models (with Tools)
Qwen3-4B-2507	34	5	1.57	7.92	28.33	11.13	15.74
Qwen3-8B	31	2	0.79	5.15	19.53	10.24	6.34
Qwen3-14B	34	9	2.36	7.11	30.23	10.17	12.64
Qwen3-32B	39	8	3.15	7.34	30.17	9.26	8.15
Qwen3-30B-A3B-2507	25	10	1.57	4.12	31.63	14.81	9.24
Ours (with Tools)
Nanbeige4-3B-2511	33	11	0.79	3.09	19.42	13.89	12.61
Nanbeige4.1-3B	75	39	19.12	31.83	69.90	22.29	41.44

Quickstart

For inference hyperparameters, we recommend the following settings:

Temperature: 0.6
Top-p: 0.95
Repeat penalty: 1.0
Max New Tokens: 131072

For the chat scenario:

from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained(
  'Nanbeige/Nanbeige4.1-3B',
  use_fast=False,
  trust_remote_code=True
)
model = AutoModelForCausalLM.from_pretrained(
  'Nanbeige/Nanbeige4.1-3B',
  torch_dtype='auto',
  device_map='auto',
  trust_remote_code=True
)
messages = [
  {'role': 'user', 'content': 'Which number is bigger, 9.11 or 9.8?'}
]
prompt = tokenizer.apply_chat_template(
  messages,
  add_generation_prompt=True,
  tokenize=False
)
input_ids = tokenizer(prompt, add_special_tokens=False, return_tensors='pt').input_ids
output_ids = model.generate(input_ids.to('cuda'), eos_token_id=166101)
resp = tokenizer.decode(output_ids[0][len(input_ids[0]):], skip_special_tokens=True)
print(resp)

For the tool use scenario:

from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained(
  'Nanbeige/Nanbeige4.1-3B',
  use_fast=False,
  trust_remote_code=True
)
model = AutoModelForCausalLM.from_pretrained(
  'Nanbeige/Nanbeige4.1-3B',
  torch_dtype='auto',
  device_map='auto',
  trust_remote_code=True
)
messages = [
    {'role': 'user',  'content': 'Help me check the weather in Beijing now'}
]
tools = [{'type': 'function',
  'function': {'name': 'SearchWeather',
   'description': 'Find out the current weather in a place on a certain day.',
   'parameters': {'type': 'dict',
    'properties': {'location': {'type': 'string',
      'description': 'A city in China.'},
    'required': ['location']}}}}]
prompt = tokenizer.apply_chat_template(
  messages,
  tools,
  add_generation_prompt=True,
  tokenize=False
)
input_ids = tokenizer(prompt, add_special_tokens=False, return_tensors='pt').input_ids
output_ids = model.generate(input_ids.to('cuda'), eos_token_id=166101)
resp = tokenizer.decode(output_ids[0][len(input_ids[0]):], skip_special_tokens=True)
print(resp)

For the deep-search scenario:

Inference Framework: miroflow-framework!
Switch tokenizer configuration to tokenizer_config_search.json
Tools Configuration:

Server	Description	Tools Provided
tool-python	Execution environment and file management (E2B sandbox)	create_sandbox, run_command, run_python_code, upload_file_from_local_to_sandbox, download_file_from_sandbox_to_local, download_file_from_internet_to_sandbox
search_and_scrape_webpage	Google search via Serper API	google_search
jina_scrape_llm_summary	Web scraping with LLM-based information extraction with Jina	scrape_and_extract_info

Summary model: Qwen3-14B-thinking
Temperature: 1.0
Note, access to HuggingFace has been explicitly disabled in these tools.

Limitations

While we place great emphasis on the safety of the model during the training process, striving to ensure that its outputs align with ethical and legal requirements, it may not completely avoid generating unexpected outputs due to the model's size and probabilistic nature. These outputs may include harmful content such as bias or discrimination. Please don't propagate such content. We do not assume any responsibility for the consequences resulting from the dissemination of inappropriate information.

Citation

If you find our model useful or want to use it in your projects, please cite as follows:

@misc{yang2026nanbeige413bsmallgeneralmodel,
      title={Nanbeige4.1-3B: A Small General Model that Reasons, Aligns, and Acts}, 
      author={Chen Yang and Guangyue Peng and Jiaying Zhu and Ran Le and Ruixiang Feng and Tao Zhang and Xiyun Xu and Yang Song and Yiming Jia and Yuntao Wen and Yunzhi Xu and Zekai Wang and Zhenwei An and Zhicong Sun and Zongchao Chen},
      year={2026},
      eprint={2602.13367},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2602.13367}, 
}

Contact

If you have any questions, please raise an issue or contact us at nanbeige@kanzhun.com.

Downloads last month: 154

GGUF

Model size

4B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for SimplySara/Nanbeige4.1-3B-GGUF

Base model

Nanbeige/Nanbeige4-3B-Base

Finetuned

Nanbeige/Nanbeige4.1-3B

Quantized

(56)

this model

Paper for SimplySara/Nanbeige4.1-3B-GGUF

Nanbeige4.1-3B: A Small General Model that Reasons, Aligns, and Acts

Paper • 2602.13367 • Published Feb 13 • 36