LLM EXPLORER 59,420 MODELS INDEXED

Gemma 1.1 2B It by google

By google · 209209 downloads
HF Repo ↗ Copy URL

Gemma 1.1 2B It is an open-source language model by google. Features: 2b LLM, VRAM: 5.1GB, Context: 8K, License: gemma, LLM Explorer Score: 0.32, ELO: 1036.

  Arxiv:1705.03551   Arxiv:1804.06876   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:2107.03374   Arxiv:2108.07732   Arxiv:2110.08193   Arxiv:2110.14168   Arxiv:2206.04615   Arxiv:2304.06364   Arxiv:2312.11805   Conversational   Endpoints compatible   Eval-results   Gemma   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/google/gemma-1.1-2b-it 

Gemma 1.1 2B It Benchmarks

LMSys ELO 1036 vs 1272 (so35) -18.6%
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Gemma 1.1 2B It Parameters and Internals

Model Type 
text generation, text-to-text, large language model, decoder-only LL
Use Cases 
Areas:
Research, Commercial applications
Applications:
Content Creation and Communication, Research and Education
Primary Use Cases:
Text Generation, Chatbots and Conversational AI, Text Summarization
Limitations:
Model's bias due to training data, Challenges with open-ended tasks
Considerations:
Continuous monitoring and detailed guidelines.
Additional Notes 
Models are state-of-the-art open large language models designed for responsible AI development.
Supported Languages 
English (Fluent)
Training Details 
Data Sources:
Web Documents, Code, Mathematics
Data Volume:
6 trillion tokens
Methodology:
Reinforcement Learning with Human Feedback (RLHF)
Context Length:
2048
Training Time:
Unknown
Hardware Used:
TPUv5e
Model Architecture:
Text-to-text, decoder-only
Safety Evaluation 
Methodologies:
Red-teaming, Automated evaluations, Human evaluation
Findings:
Acceptable thresholds for internal policies, Results on well-known safety benchmarks
Risk Categories:
Child safety, Content safety, Representational harms, Memorization risks, Large-scale harms
Ethical Considerations:
Various safety benchmarks and internal evaluation methods applied.
Responsible Ai Considerations 
Fairness:
Careful pre-processing and evaluation to mitigate biases
Transparency:
Open model with summarized details on architecture and capabilities
Accountability:
Development of mechanisms and guidelines for content safety
Mitigation Strategies:
Techniques for de-biasing and content flagging guidelines
Input Output 
Input Format:
Text string
Accepted Modalities:
text
Output Format:
Generated text
Performance Tips:
Addition of appropriate content context can improve performance.
Release Notes 
Version:
1.1
Date:
Unknown
Notes:
Substantial gains with improved RLHF method and resolved multi-turn conversation bug.
LLM NameGemma 1.1 2B It
Repository 🤗https://huggingface.co/google/gemma-1.1-2b-it 
Model Size2b
Required VRAM5.1 GB
Updated2026-08-06
Maintainergoogle
Model Typegemma
Model Files  5.0 GB: 1-of-2   0.1 GB: 2-of-2
Model ArchitectureGemmaForCausalLM
Licensegemma
Context Length8192
Model Max Length8192
Transformers Version4.38.1
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size256000
Torch Data Typebfloat16

Quantized Models of the Gemma 1.1 2B It

Model
Likes
Downloads
VRAM
Gemma 1.1 2B It GPTQ1338343 GB
Gemma 1.1 2B It 4bit31582 GB
Gemma 1.1 2B It GGUF01221 GB
Gemma 1.1 2B It AWQ143 GB

Best Alternatives to Gemma 1.1 2B It

Best Alternatives
Context / RAM
Downloads
Likes
Gemma 2B It8K / 5 GB168023
Gemma 1.1 2B It8K / 5 GB433
Gemma 2B It Peru Legal Es V28K / 5.1 GB81
Codegemma 2B8K / 5.1 GB33091101
Bge Reranker V2 Gemma8K / 10 GB24549087
Gita SastraGPT V18K / 5.1 GB41
Caca Tinny 2B V38K / 5.1 GB41
Pandas Tutor Gemma 2B8K / 5.1 GB61
Gemma Qlora Customer Support8K / 5.1 GB80
... 2B Finetuned Sft Navarasa 2.08K / 10 GB53627