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 2B It by google

 »  All LLMs  »  google  »  Gemma 2B It   URL Share it on

  56607   

Gemma 2B It is an open-source language model by google. Features: 2b LLM, VRAM: 5.1GB, Context: 8K, License: gemma, Quantized, HF Score: 42.8, LLM Explorer Score: 0.39, ELO: 1004, Arc: 43.9, HellaSwag: 62.7, MMLU: 37.7, TruthfulQA: 45.8, WinoGrande: 60.9, GSM8K: 5.5.

  Arxiv:1705.03551   Arxiv:1804.06876   Arxiv:1804.09301   Arxiv:1809.02789   Arxiv:1811.00937   Arxiv:1904.09728   Arxiv:1905.07830   Arxiv:1905.10044   Arxiv:1907.10641   Arxiv:1911.01547   Arxiv:1911.11641   Arxiv:2009.03300   Arxiv:2009.11462   Arxiv:2101.11718   Arxiv:2107.03374   Arxiv:2108.07732   Arxiv:2109.07958   Arxiv:2110.08193   Arxiv:2110.14168   Arxiv:2203.09509   Arxiv:2206.04615   Arxiv:2304.06364   Arxiv:2312.11805   Conversational   Endpoints compatible   Gemma   Gguf   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/google/gemma-2b-it 

Gemma 2B It Benchmarks

LMSys ELO: 1004 vs 1272 (so35)-21.1%
MMLU Pro: 3.92
GPQA: 3.8
MUSR: 3.03
BBH: 5.21
IFEval: 26.9 vs 88 (so35)-69.4%
ARC: 43.94 vs 96.7 (so35)-54.6%
HellaSwag: 62.7 vs 95.3 (gpt4)-34.2%
MMLU: 37.65 vs 88.3 (so35)-57.4%
TruthfulQA: 45.82 vs 59 (gpt4)-22.3%
WinoGrande: 60.93 vs 87.5 (gpt4)-30.4%
GSM8K: 5.46 vs 96.4 (so35)-94.3%
MATH Lvl 5: 2.04
LLME Score: 0.38699
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Gemma 2B It (google/gemma-2b-it)
🌟 Advertise your project 🚀

Gemma 2B It Parameters and Internals

Model Type 
text generation, decoder-only
Use Cases 
Areas:
Content creation, Research and education
Applications:
Text generation, Chatbots, Text summarization
Primary Use Cases:
Creative text formats, NLP research, Language learning tools
Limitations:
Bias from training data, Complex task handling limitations
Considerations:
Use with caution for sensitive or biased scenarios.
Additional Notes 
Open models from Google, built from Gemini technology.
Supported Languages 
English (High proficiency)
Training Details 
Data Sources:
Web Documents, Code, Mathematics
Data Volume:
6 trillion tokens
Methodology:
Decoder-only model trained with TPUs, using JAX and ML Pathways
Hardware Used:
TPUv5e
Model Architecture:
Lightweight, state-of-the-art open model
Safety Evaluation 
Methodologies:
Red-teaming, Human evaluation, Automated evaluation
Findings:
Within acceptable thresholds
Risk Categories:
CSAM, Sensitive Data Filtering, Large-scale harm
Ethical Considerations:
Evaluation included representational harms, content safety, and memorization risks.
Responsible Ai Considerations 
Fairness:
Model includes multiple stages of filtering for potentially harmful content.
Transparency:
Model architecture, training, and evaluation details are publicized.
Accountability:
Google is accountable for the content and safety evaluations.
Mitigation Strategies:
Mechanisms were instituted for content safety and bias reduction.
Input Output 
Input Format:
Text string
Accepted Modalities:
text
Output Format:
Generated English-language text
Performance Tips:
None specified
Release Notes 
Version:
gemma-2b-it
Date:
Not specified
Notes:
2B instruct version.
Version:
7B base model
Date:
Not specified
Notes:
Larger variant of the model.
Version:
7B instruct model
Date:
Not specified
Notes:
Instruction-tuned variant.
LLM NameGemma 2B It
Repository 🤗https://huggingface.co/google/gemma-2b-it 
Base Model(s)  Gemma 2B Tr   Metin/gemma-2b-tr
Model Size2b
Required VRAM5.1 GB
Updated2026-04-06
Maintainergoogle
Model Typegemma
Model Files  10.0 GB   5.0 GB: 1-of-2   0.1 GB: 2-of-2
GGUF QuantizationYes
Quantization Typegguf
Model ArchitectureGemmaForCausalLM
Licensegemma
Context Length8192
Model Max Length8192
Transformers Version4.38.0.dev0
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size256000
Torch Data Typebfloat16

Quantized Models of the Gemma 2B It

Model
Likes
Downloads
VRAM
Gemma 2B DPO Uncensored 4bit624995 GB
Gemma 2B It GGUF106311 GB
Gemma 2B It GGUF54500 GB
Gemma 2B It GGUF0751 GB
...ummarization T4 4bit Notmerged050 GB

Best Alternatives to Gemma 2B It

Best Alternatives
Context / RAM
Downloads
Likes
Gemma 2B8K / 5.1 GB1849151091
Gemma 2B It8K / 1.5 GB170
Gemma 2B It8K / 5.1 GB341
Gemma 2B T8K / 5.1 GB120
Gemma 2B It Code8K / 5.1 GB130
Gemma 2B It Q8K / 1.6 GB271
Gemma Help Tiny Sft8K / 5.1 GB141
Gemma 2B It Q4 K M GGUF8K / 1.6 GB14125
GemSUra Edu8K / 5 GB760
...mma 2b Sauerkraut Gguf Chunked8K / 0.1 GB750

Rank the Gemma 2B 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? 52721 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