LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Gemma 2B Int4 Inc by Intel

 »  All LLMs  »  Intel  »  Gemma 2B Int4 Inc   URL Share it on

  38   
  4-bit   Autotrain compatible   Dataset:neelnanda/pile-10k   Endpoints compatible   Gemma   Gptq   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/Intel/gemma-2b-int4-inc 

Gemma 2B Int4 Inc Benchmarks

LLME Score: 0.14762
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Gemma 2B Int4 Inc (Intel/gemma-2b-int4-inc)
🌟 Advertise your project 🚀

Gemma 2B Int4 Inc Parameters and Internals

Model Type 
int4, transformers, causal-lm
Use Cases 
Primary Use Cases:
INT4 Inference with ITREX on CPU, INT4 Inference with AutoGPTQ's kernel
Limitations:
Can produce factually incorrect output., May generate lewd, biased, or offensive content.
Considerations:
Users should be aware of risks, biases, and limitations.
Additional Notes 
Intel's AI software includes Neural Compressor and Extension for Transformers.
Training Details 
Data Sources:
NeelNanda/pile-10k
Methodology:
INT4 quantization using AutoRound
Hardware Used:
CPU
Responsible Ai Considerations 
Fairness:
It can produce biased outputs due to limitations in the pre-training and fine-tuning datasets.
Transparency:
Model card provided with known limitations and biases.
Accountability:
Developers should perform safety testing and are accountable for model outputs in deployed applications.
Mitigation Strategies:
Perform safety testing before deployment.
Input Output 
Input Format:
Input text sequence.
Accepted Modalities:
text
Output Format:
Generated text sequence.
Performance Tips:
Utilize ITREX and AutoGPTQ for enhanced performance.
LLM NameGemma 2B Int4 Inc
Repository 🤗https://huggingface.co/Intel/gemma-2b-int4-inc 
Model Size2b
Required VRAM3.1 GB
Updated2025-09-12
MaintainerIntel
Model Typegemma
Model Files  3.1 GB
Model ArchitectureGemmaForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.40.2
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size256000
Torch Data Typefloat16

Best Alternatives to Gemma 2B Int4 Inc

Best Alternatives
Context / RAM
Downloads
Likes
Gemma 1.1 2B It8K / 5.1 GB280063165
Gita SastraGPT V18K / 5.1 GB1161
Codegemma 2B8K / 5.1 GB2390285
Caca Tinny 2B V38K / 5.1 GB151
Pandas Tutor Gemma 2B8K / 5.1 GB131
Gemma Qlora Customer Support8K / 5.1 GB100
Gemma Ko 1.1 2B It8K / 5.1 GB10741
... 2B Finetuned Sft Navarasa 2.08K / 10 GB117125
Octopus V28K / 5.1 GB1401889
Octopus V28K / 5.1 GB1387885
Note: green Score (e.g. "73.2") means that the model is better than Intel/gemma-2b-int4-inc.

Rank the Gemma 2B Int4 Inc 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? 51317 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