What are the hardware requirements for Nanbeige4.1 3B?

Nanbeige4.1 3B requires approximately 7.9 GB of VRAM and supports a context window of 256K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Nanbeige4.1 3B and how large is it?

Nanbeige4.1 3B is developed by Nanbeige, a model with 3b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Nanbeige4.1 3B?

Nanbeige4.1 3B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Nanbeige4.1 3B by Nanbeige — VRAM 7.9GB, 256K context

Name: Nanbeige4.1 3B
Author: Nanbeige

Nanbeige4.1 3B is an open-source language model by Nanbeige. Features: 3b LLM, VRAM: 7.9GB, Context: 256K, License: apache-2.0, LLM Explorer Score: 0.43.

Arxiv:2602.13367 Base model:finetune:nanbeige/n... Base model:nanbeige/nanbeige4-... Conversational Deploy:azure En Endpoints compatible Eval-results Llama Nanbeige Region:us Safetensors Sharded Tensorflow Zh

Model Card on HF 🤗: https://huggingface.co/Nanbeige/Nanbeige4.1-3B

Nanbeige4.1 3B Benchmarks

LLME Score: 0.42662

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

Nanbeige4.1 3B (Nanbeige/Nanbeige4.1-3B)

🌟 Advertise your project 🚀

Nanbeige4.1 3B Parameters and Internals

LLM Name	Nanbeige4.1 3B
Repository 🤗	https://huggingface.co/Nanbeige/Nanbeige4.1-3B
Base Model(s)	Nanbeige4 3B Base Nanbeige/Nanbeige4-3B-Base
Model Size	3b
Required VRAM	7.9 GB
Updated	2026-05-26
Maintainer	Nanbeige
Model Type	llama
Model Files	5.0 GB: 1-of-2 2.9 GB: 2-of-2
Supported Languages	en zh
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	262144
Model Max Length	262144
Transformers Version	4.51.3
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	166144
Torch Data Type	bfloat16

Quantized Models of the Nanbeige4.1 3B

Model	Likes	Downloads	VRAM
...eige 4.1 3B Deepseek Distilled	3	2704	15 GB
Nanbeige4.1 3B 8bit	14	255	4 GB

Best Alternatives to Nanbeige4.1 3B

Best Alternatives	Context / RAM	Downloads	Likes
Nanbeige4.1 3B Heretic	256K / 7.9 GB	393	50
Nanbeige4.1 3B Bf16	256K / 7.9 GB	71	3
Nanbeige4.1 3B Heretic Mxfp4	256K / 7.9 GB	44	2
Nanbeige4.1 3B Heretic	256K / 7.9 GB	5	1
Nanbeige4.1 3B Heretic	256K / 7.9 GB	5	0
ISA 03 Mini 3B Hybrid Preview	256K / 6.5 GB	851	4
Llama 3.2 3B Instruct	128K / 6.5 GB	2205212	2139
Llama 3.2 3B	128K / 6.5 GB	1183471	785
Llama 3.2 3B Instruct	128K / 6.5 GB	1237	9
DeepSeek R1 Distill Llama 3B	128K / 6.5 GB	1740	16

Rank the Nanbeige4.1 3B Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

What open-source LLMs or SLMs are you in search of? 54529 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Check out Ag3ntum — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer

Nanbeige4.1 3B by Nanbeige