LLM EXPLORER 60,783 MODELS INDEXED

Gemma 7B It by google

By google · 24944 downloads
HF Repo ↗ Copy URL

Gemma 7B It is an open-source language model by google. Features: 7b LLM, VRAM: 17.1GB, Context: 8K, License: gemma, Quantized, LLM Explorer Score: 0.36, ELO: 1052, Arc: 51.5, HellaSwag: 72, MMLU: 53.5, GSM8K: 29.2.

  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 Base model:finetune:google/gem...   Base model:google/gemma-7b   Conversational   Deploy:sagemaker   Endpoints compatible   Eval-results   Gemma   Gguf   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/google/gemma-7b-it 

Gemma 7B It Benchmarks

LMSys ELO 1052 vs 1272 (so35) -17.3%
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Gemma 7B It Parameters and Internals

Model Type 
Text-to-text, Decoder-only large language models
Use Cases 
Areas:
Content Creation, Research, Education
Applications:
Text Generation, Chatbots, Text Summarization
Limitations:
Training data limitations, Context and task complexity, Language ambiguity, Factual accuracy issues
Considerations:
Guidelines provided for responsible use.
Supported Languages 
English (fluent)
Training Details 
Data Sources:
Web Documents, Code, Mathematics
Data Volume:
6 trillion tokens
Hardware Used:
TPUv5e
Safety Evaluation 
Methodologies:
Structured evaluations, Internal red-teaming
Findings:
Acceptable thresholds for internal policies
Risk Categories:
Child safety, Content safety, Representational harms, Memorization, Large-scale harms
Ethical Considerations:
Responsible Ai Considerations 
Fairness:
Scrutiny and data pre-processing done to mitigate biases.
Transparency:
Model card provides details on architecture, capabilities, and processes.
Accountability:
Google as the developer has oversight on model deployments.
Mitigation Strategies:
Developers are encouraged to follow guidelines for responsible use.
Input Output 
Input Format:
Text string (e.g., prompt or question)
Output Format:
Generated English-language text
LLM NameGemma 7B It
Repository 🤗https://huggingface.co/google/gemma-7b-it 
Base Model(s)  Gemma 7B   google/gemma-7b
Model Size7b
Required VRAM17.1 GB
Updated2026-08-07
Maintainergoogle
Model Typegemma
Model Files  34.2 GB   5.0 GB: 1-of-4   5.0 GB: 2-of-4   5.0 GB: 3-of-4   2.1 GB: 4-of-4
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 7B It

Model
Likes
Downloads
VRAM
Gemma 7B It GGUF88263 GB
Gemma 7B It GGUF114573 GB

Best Alternatives to Gemma 7B It

Best Alternatives
Context / RAM
Downloads
Likes
Gemma 7B8K / 17.1 GB290513388
Gemma 1.1 7B It GGUF8K / 5.3 GB521
Train068K / 9.1 GB220
Llama2 Kazakh 7B GGUF8K / 4.1 GB100
Gemma 7B8K / 17.1 GB390
Gemma 7B Translator 0.48K / 17.1 GB390
Gemma 7B Translator 0.38K / 17.1 GB360
Gemma7B Konosuba8K / 17.1 GB201
Gemma 7B It GGUF8K / 5.3 GB611
Gemma 7B It GGUF8K / 3.1 GB45711