LLM EXPLORER 60,384 MODELS INDEXED

Qwen3 4B RP V3 by bunnycore

By bunnycore · 19 downloads
HF Repo ↗ Copy URL

Qwen3 4B RP V3 is an open-source language model by bunnycore. Features: 4b LLM, VRAM: 8GB, Context: 40K, Merged, LLM Explorer Score: 0.18.

  Merged Model   Arxiv:2306.01708 Base model:bunnycore/qwen3-4b-... Base model:ertghiu256/qwen-3-4... Base model:fakezeta/amoral-qwe... Base model:huihui-ai/huihui-qw... Base model:superbemphasis/qwen...   Endpoints compatible   Qwen3   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/bunnycore/Qwen3-4B-RP-V3 

Qwen3 4B RP V3 Parameters and Internals

LLM NameQwen3 4B RP V3
Repository 🤗https://huggingface.co/bunnycore/Qwen3-4B-RP-V3 
Base Model(s)  Qwen 3 4B Mixture Of Thought   Qwen3 4B RP Test   Qwen3 4B RP V2   Amoral Qwen3 4B   Huihui Qwen3 4B Abliterated V2   ertghiu256/qwen-3-4b-mixture-of-thought   SuperbEmphasis/Qwen3-4B-RP-Test   bunnycore/Qwen3-4B-RP-V2   fakezeta/amoral-Qwen3-4B   huihui-ai/Huihui-Qwen3-4B-abliterated-v2
Merged ModelYes
Model Size4b
Required VRAM8 GB
Updated2026-07-15
Maintainerbunnycore
Model Typeqwen3
Model Files  5.0 GB: 1-of-2   3.0 GB: 2-of-2
Model ArchitectureQwen3ForCausalLM
Context Length40960
Model Max Length40960
Transformers Version4.52.4
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typefloat16
Errorsreplace

Best Alternatives to Qwen3 4B RP V3

Best Alternatives
Context / RAM
Downloads
Likes
FastContext 1.0 4B SFT256K / 8.1 GB5735357
Qwen3 4B Instruct 2507256K / 8.1 GB3109972911
GRPO 4 70256K / 8.1 GB150
...2.5 Flash Lite Preview Distill256K / 8.1 GB311
Lightning 4B256K / 8.1 GB136
Fable Traces256K / 8.1 GB385210
Checkpoint 8000256K / 8.1 GB14530
Qwen3 4B Thinking 2507256K / 8.1 GB291023606
FastContext 1.0 4B RL256K / 8.1 GB455961
Qwen3 4B Instruct 2507 FP8256K / 5.2 GB110074478
Note: green Score (e.g. "73.2") means that the model is better than bunnycore/Qwen3-4B-RP-V3.