What are the hardware requirements for Dare4b?

Dare4b requires approximately 9.1 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Dare4b and how large is it?

Dare4b is developed by DareModels, 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 Dare4b?

Dare4b is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Dare4b by DareModels — VRAM 9.1GB

Name: Dare4b
Author: DareModels

Dare4b is an open-source language model by DareModels. Features: 4b LLM, VRAM: 9.1GB, Code Generating, Merged, LLM Explorer Score: 0.25.

Merged Model Arxiv:2311.03099 Base model:baai/arex-turbo Base model:br1-pist/qwen3.5-4b... Base model:cloudgoat/mephisto-... Base model:hotdogs/agents-a1-4... Base model:shuhulx/qwopus3.5-4... Codegen Conversational Endpoints compatible Image-text-to-text Qwen3 5 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/DareModels/dare4b

Dare4b Parameters and Internals

LLM Name	Dare4b
Repository 🤗	https://huggingface.co/DareModels/dare4b
Base Model(s)	AREX Turbo ...ts A1 4B Fable Preview Heretic Mephisto 4B 0725 br1-pist/Qwen3.5-4B-AgentCoder shuhulx/Qwopus3.5-4B-Coder-Fable5-v1 BAAI/AREX-Turbo hotdogs/Agents-A1-4B-Fable-Preview-heretic CloudGoat/Mephisto-4B-0725 br1-pist/Qwen3.5-4B-AgentCoder shuhulx/Qwopus3.5-4B-Coder-Fable5-v1
Merged Model	Yes
Model Size	4b
Required VRAM	9.1 GB
Updated	2026-09-29
Maintainer	DareModels
Model Type	qwen3_5
Model Files	5.0 GB: 1-of-2 4.1 GB: 2-of-2
Generates Code	Yes
Model Architecture	Qwen3_5ForConditionalGeneration
Model Max Length	262144
Transformers Version	5.12.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Dare4b capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

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

Best Alternatives to Dare4b

Best Alternatives	Context / RAM	Downloads	Likes
Qwopus3.5 4B Coder Fable5 V1	0K / 9.3 GB	159	1
Qwen3.5 4B Agentic Coder V4	0K / 9.3 GB	51	2

Note: green Score (e.g. "73.2") means that the model is better than DareModels/dare4b.