LLM EXPLORER 56,604 MODELS INDEXED

Dare4b by DareModels

By DareModels · 66 downloads
HF Repo ↗ Copy URL

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

  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 NameDare4b
Repository 🤗https://huggingface.co/DareModels/dare4b 
Base Model(s)  BAAI/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 ModelYes
Model Size4b
Required VRAM9.1 GB
Updated2026-08-09
MaintainerDareModels
Model Typeqwen3_5
Model Files  5.0 GB: 1-of-2   4.1 GB: 2-of-2
Generates CodeYes
Model ArchitectureQwen3_5ForConditionalGeneration
Model Max Length262144
Transformers Version5.12.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace