LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Qwen3 4B Merge Variant 01 by Felladrin

 »  All LLMs  »  Felladrin  »  Qwen3 4B Merge Variant 01   URL Share it on

  6   

Qwen3 4B Merge Variant 01 is an open-source language model by Felladrin. Features: 4b LLM, VRAM: 16.1GB, Context: 40K, License: apache-2.0, Merged, LLM Explorer Score: 0.19.

  Merged Model   Arxiv:2406.11617   Base model:menlo/jan-nano-128k Base model:mlabonne/qwen3-4b-a... Base model:polaris-project/pol... Base model:valiantlabs/qwen3-4...   Conversational   Endpoints compatible   Qwen3   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Felladrin/Qwen3-4B-Merge-Variant-01 

Qwen3 4B Merge Variant 01 Benchmarks

LLME Score: 0.19347
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen3 4B Merge Variant 01 (Felladrin/Qwen3-4B-Merge-Variant-01)
🌟 Advertise your project 🚀

Qwen3 4B Merge Variant 01 Parameters and Internals

LLM NameQwen3 4B Merge Variant 01
Repository 🤗https://huggingface.co/Felladrin/Qwen3-4B-Merge-Variant-01 
Base Model(s)  Jan Nano 128K   Polaris 4B Preview   Qwen3 4B Abliterated   Qwen3 4B Esper3   Menlo/Jan-nano-128k   POLARIS-Project/Polaris-4B-Preview   mlabonne/Qwen3-4B-abliterated   ValiantLabs/Qwen3-4B-Esper3
Merged ModelYes
Model Size4b
Required VRAM16.1 GB
Updated2026-04-19
MaintainerFelladrin
Model Typeqwen3
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   5.0 GB: 3-of-4   1.1 GB: 4-of-4
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length40960
Model Max Length40960
Transformers Version4.51.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typefloat32
Errorsreplace

Best Alternatives to Qwen3 4B Merge Variant 01

Best Alternatives
Context / RAM
Downloads
Likes
FastContext 1.0 4B SFT256K / 8.1 GB5735357
FastContext 1.0 4B RL256K / 8.1 GB353359
Qwen3 4B Instruct 2507256K / 8.1 GB4833125869
GRPO 4 70256K / 8.1 GB50
Qwen3 4B Thinking 2507256K / 8.1 GB599357591
Lightning 4B256K / 8.1 GB136
Qwen3 4B Instruct 2507 FP8256K / 5.2 GB84028179
Jan V1 4B256K / 8.1 GB108354353
AgentCPM Explore256K / 8.9 GB499415
OpenSonnet Lite MAX256K / 8 GB40530
Note: green Score (e.g. "73.2") means that the model is better than Felladrin/Qwen3-4B-Merge-Variant-01.

Rank the Qwen3 4B Merge Variant 01 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? 54597 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