What are the hardware requirements for Qwen3 4B New?

Qwen3 4B New requires approximately 8 GB of VRAM and supports a context window of 40K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen3 4B New and how large is it?

Qwen3 4B New is developed by boradorish, a model with 4b 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 Qwen3 4B New?

Qwen3 4B New is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Qwen3 4B New by boradorish — VRAM 8GB, 40K context

Name: Qwen3 4B New
Author: boradorish

Qwen3 4B New is an open-source language model by boradorish. Features: 4b LLM, VRAM: 8GB, Context: 40K, License: other, LLM Explorer Score: 0.29.

Base model:finetune:qwen/qwen3... Base model:qwen/qwen3-4b Conversational Endpoints compatible Full Generated from trainer Llama-factory Qwen3 Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/boradorish/qwen3-4b-new

Qwen3 4B New Benchmarks

LLME Score: 0.29025

^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)

🌟 Advertise your project 🚀

Qwen3 4B New Parameters and Internals

LLM Name	Qwen3 4B New
Repository 🤗	https://huggingface.co/boradorish/qwen3-4b-new
Base Model(s)	Qwen/Qwen3-4B Qwen/Qwen3-4B
Model Size	4b
Required VRAM	8 GB
Updated	2026-05-19
Maintainer	boradorish
Model Type	qwen3
Model Files	8.0 GB 0.0 GB
Model Architecture	Qwen3ForCausalLM
License	other
Context Length	40960
Model Max Length	40960
Transformers Version	5.6.0
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151936
Errors	replace

Best Alternatives to Qwen3 4B New

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3 4B Instruct 2507	256K / 8.1 GB	10823759	832
GRPO 4 70	256K / 8.1 GB	5	0
Qwen3 4B Thinking 2507	256K / 8.1 GB	830285	581
Lightning 4B	256K / 8.1 GB	13	6
ChineseErrorCorrector4 4B	256K / 8.1 GB	44	4
Jan V1 4B	256K / 8.1 GB	108354	353
Qwen3 4B Instruct 2507 FP8	256K / 5.2 GB	803780	75
OpenSonnet Lite MAX	256K / 8 GB	54	21
AgentCPM Explore	256K / 8.9 GB	204	413
Base Th Sft Translate 4B	256K / 8.1 GB	560	0

Note: green Score (e.g. "73.2") means that the model is better than boradorish/qwen3-4b-new.

Rank the Qwen3 4B New 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? 53834 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

Qwen3 4B New by boradorish

» All LLMs » boradorish » Qwen3 4B New URL Share it on

Qwen3 4B New Benchmarks

Qwen3 4B New Parameters and Internals

Best Alternatives to Qwen3 4B New

Rank the Qwen3 4B New Capabilities

What open-source LLMs or SLMs are you in search of? 53834 in total.