Gemma 2B By google: Benchmarks, Features and Detailed Analysis. Insights on Gemma 2B.

Model Card on HF 🤗: https://huggingface.co/google/gemma-2b

Gemma 2B Benchmarks

MMLU Pro: 4.06

GPQA: 0.67

MUSR: 7.56

BBH: 8.25

IFEval: 20.38 vs 88 (so35)^-76.8%

ARC: 48.38 vs 96.7 (so35)^-50%

HellaSwag: 71.77 vs 95.3 (gpt4)^-24.7%

MMLU: 41.77 vs 88.3 (so35)^-52.7%

TruthfulQA: 33.08 vs 59 (gpt4)^-43.9%

WinoGrande: 66.3 vs 87.5 (gpt4)^-24.2%

GSM8K: 16.91 vs 96.4 (so35)^-82.5%

MATH Lvl 5: 3.02

LLME Score: 0.32956

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

What is the LLM Explorer Rank (Score)

🌟 Advertise your project 🚀

Gemma 2B Parameters and Internals

Model Type

text-to-text, decoder-only, large language model

Use Cases

Areas:

Various industries and domains

Applications:

Content Creation and Communication, Research and Education

Primary Use Cases:

Text Generation, Chatbots and Conversational AI, Text Summarization, NLP Research, Language Learning, Knowledge Exploration

Limitations:

Bias and Fairness, Misinformation and Misuse, Lack of Common Sense, Factual Inaccuracy

Considerations:

LLMs performance is heavily dependent on the quality of input prompts and the context length.

Additional Notes

This description is based on the specified version, other iteration details can be found in technical documents.

Supported Languages

English (available for text generation, question answering, summarization, and reasoning tasks)

Training Details

Data Sources:

Web Documents, Code, Mathematics

Data Volume:

6 trillion tokens

Methodology:

Rigorous CSAM filtering, Sensitive Data Filtering, filtering based on content quality and safety

Context Length:

8192

Hardware Used:

TPUv5e, TPU Pods

Model Architecture:

JAX and ML Pathways

Safety Evaluation

Methodologies:

Red-teaming, Structured evaluations

Risk Categories:

Text-to-Text Content Safety, Text-to-Text Representational Harms, Memorization, Large-scale harm

Ethical Considerations:

Models evaluated against a number of different categories relevant to ethics and safety, include Text-to-Text Content Safety, Representational Harms, potential data memorization, and dangerous capability tests.

Responsible Ai Considerations

Fairness:

These models underwent careful scrutiny and input data pre-processing with posterior evaluations reported in this card.

Transparency:

The model card summarizes details on the models' architecture, capabilities, limitations, and evaluation processes.

Accountability:

Google is accountable for the use of the model under its terms of service and policies.

Mitigation Strategies:

Developers are encouraged to monitor and report misuse, employ de-biasing techniques, implement content safety safeguards, and adhere to privacy regulations.

Input Output

Input Format:

Text string

Accepted Modalities:

text

Output Format:

Generated English-language text

Performance Tips:

Ensure to use correct input formats for fine-tuning or inference, use optimizations for specific hardware and quantization methods.

Release Notes

Version:

v1.1 IT

Notes:

Contains updates and new numbers for the IT version models, surpasses previous versions across various benchmarks.

LLM Name	Gemma 2B
Repository 🤗	https://huggingface.co/google/gemma-2b
Base Model(s)	Google Gemma 2B 1719012541 richardkelly/google-gemma-2b-1719012541
Model Size	2b
Required VRAM	5.1 GB
Updated	2025-10-19
Maintainer	google
Model Type	gemma
Model Files	10.0 GB 5.0 GB: 1-of-2 0.1 GB: 2-of-2
GGUF Quantization	Yes
Quantization Type	gguf
Model Architecture	GemmaForCausalLM
License	gemma
Context Length	8192
Model Max Length	8192
Transformers Version	4.38.0.dev0
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>
Vocabulary Size	256000
Torch Data Type	bfloat16

Quantized Models of the Gemma 2B

Model	Likes	Downloads	VRAM
Octopus V2 Gguf AWQ	7	3055	1 GB
Octopus V2 Gguf AWQ	7	1577	1 GB
Gemma 2B GGUF	6	502	1 GB
Gemma 2B GGUF	0	59	1 GB
Physicsgemma2bAlpaca	0	16	2 GB

Best Alternatives to Gemma 2B

Best Alternatives	Context / RAM	Downloads	Likes
Gemma 2B It	8K / 5.1 GB	234475	800
Gemma 2B It	8K / 1.5 GB	11	0
Gemma 2B It	8K / 5.1 GB	17	1
Gemma 2B T	8K / 5.1 GB	6	0
Gemma 2B It Code	8K / 5.1 GB	14	0
Gemma 2B It Q	8K / 1.6 GB	62	1
Gemma Help Tiny Sft	8K / 5.1 GB	132	1
Gemma 2B It Q4 K M GGUF	8K / 1.6 GB	2096	3
...mma 2b Sauerkraut Gguf Chunked	8K / 0.1 GB	138	0
GemSUra Edu	8K / 5 GB	21	0

Note: green Score (e.g. "73.2") means that the model is better than google/gemma-2b.

Rank the Gemma 2B 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? 51544 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.

Release v20241124

Support LLM Explorer