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

Gemma 3 4B T1 It by twinkle-ai

 »  All LLMs  »  twinkle-ai  »  Gemma 3 4B T1 It   URL Share it on

  8430   

Gemma 3 4B T1 It is an open-source language model by twinkle-ai. Features: 4b LLM, VRAM: 9.1GB, Context: 128K, License: gemma, Instruction-Based, LLM Explorer Score: 0.43, ELO: 1303.

Base model:finetune:google/gem... Base model:google/gemma-3-4b-p... Dataset:lianghsun/tw-contract-... Dataset:lianghsun/tw-reasoning... Dataset:minyichen/longpaper mu... Dataset:minyichen/tw-instruct-...   Dataset:minyichen/tw mm r1 Dataset:nvidia/nemotron-instru...   En   Endpoints compatible   Gemma-3   Gemma3   Gemma3 text   Instruct   Model-index   R.o.c   Region:us   Safetensors   Sharded   Slm   Taiwan   Tensorflow   Zh   Zhtw
Model Card on HF 🤗: https://huggingface.co/twinkle-ai/gemma-3-4B-T1-it 

Gemma 3 4B T1 It Benchmarks

LMSys ELO: 1303 vs 1272 (so35)2.4%
LLME Score: 0.42684
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Gemma 3 4B T1 It (twinkle-ai/gemma-3-4B-T1-it)
🌟 Advertise your project 🚀

Gemma 3 4B T1 It Parameters and Internals

LLM NameGemma 3 4B T1 It
Repository 🤗https://huggingface.co/twinkle-ai/gemma-3-4B-T1-it 
Base Model(s)  google/gemma-3-4b-pt   google/gemma-3-4b-pt
Model Size4b
Required VRAM9.1 GB
Updated2026-05-21
Maintainertwinkle-ai
Model Typegemma3_text
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   4.1 GB: 2-of-2
Supported Languagesen zh
Model ArchitectureGemma3ForCausalLM
Licensegemma
Context Length131072
Model Max Length131072
Transformers Version4.55.2
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size262208
Torch Data Typebfloat16

Best Alternatives to Gemma 3 4B T1 It

Best Alternatives
Context / RAM
Downloads
Likes
KONI 4B Instruct 20250901128K / 7.8 GB132

Rank the Gemma 3 4B T1 It 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? 53999 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