LLM EXPLORER 59,420 MODELS INDEXED

Gemma 1.1 2B It AWQ by TechxGenus

By TechxGenus · 4 downloads
HF Repo ↗ Copy URL

Gemma 1.1 2B It AWQ is an open-source language model by TechxGenus. Features: 2b LLM, VRAM: 3.1GB, Context: 8K, License: gemma, Quantized, LLM Explorer Score: 0.12.

  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   4-bit   Awq   Conversational   Endpoints compatible   Gemma   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TechxGenus/gemma-1.1-2b-it-AWQ 

Gemma 1.1 2B It AWQ Parameters and Internals

Model Type 
text-to-text, decoder-only, large language model
Use Cases 
Areas:
Research, Commercial applications
Applications:
Text Generation, Chatbots, Text Summarization, Research, Language Learning
Primary Use Cases:
Question answering, Summarization, Reasoning
Limitations:
Open-ended, highly complex tasks may be challenging, Lacks deep common sense reasoning
Considerations:
Consider dataset biases and misuse potential.
Additional Notes 
Encouraged feedback from community. Open model for access to innovative AI.
Supported Languages 
English (native)
Training Details 
Data Sources:
Web Documents, Code, Mathematics
Data Volume:
6 trillion tokens
Methodology:
Trained using RLHF and instruction-tuned techniques
Hardware Used:
TPUv5e
Model Architecture:
Large language model with text-to-text and decoder-only architecture.
Safety Evaluation 
Methodologies:
Red-teaming, Human Evaluation, Automated Testing
Findings:
Models evaluated for content safety, representational harms, memorization, large-scale harm risks., Within acceptable thresholds for internal policies.
Risk Categories:
Child Safety, Content Safety, Representational Harms, Memorization, Dangerous Capabilities
Ethical Considerations:
Monitored for biases and adjusted to mitigate representation harms.
Responsible Ai Considerations 
Fairness:
Monitored biases, using evaluations like WinoBias and BBQ.
Transparency:
Open model details summarised in model card.
Accountability:
Developed and maintained by Google with published guidelines for responsible use.
Mitigation Strategies:
Filtering training data, using responsible AI toolkit guidelines.
Input Output 
Input Format:
Text string
Accepted Modalities:
text
Output Format:
Generated English-language text
Performance Tips:
Longer context generally leads to better outputs.
Release Notes 
Version:
1.1
Date:
unknown
Notes:
Update with RLHF method, improvements in quality & factuality.
LLM NameGemma 1.1 2B It AWQ
Repository 🤗https://huggingface.co/TechxGenus/gemma-1.1-2b-it-AWQ 
Base Model(s)  google/gemma-1.1-2b-it   google/gemma-1.1-2b-it
Model Size2b
Required VRAM3.1 GB
Updated2026-07-28
MaintainerTechxGenus
Model Typegemma
Model Files  3.1 GB
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureGemmaForCausalLM
Licensegemma
Context Length8192
Model Max Length8192
Transformers Version4.39.3
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size256000
Torch Data Typefloat16

Best Alternatives to Gemma 1.1 2B It AWQ

Best Alternatives
Context / RAM
Downloads
Likes
... Codegemma 2B AWQ 4bit Smashed8K / 3.1 GB2340
Codegemma 1.1 2B AWQ8K / 3.1 GB120
Gemma 2B It AWQ8K / 3.1 GB950
Gemma 2B AWQ8K / 3.1 GB140
... 2B It Hermes Function Calling8K / 5.1 GB180
Octopus V2 Gguf AWQ8K / 1.2 GB23567
Octopus V2 Gguf AWQ8K / 1.2 GB15777
Vi Gemma 2B RAG8K / 5.1 GB3613
My AwesomeFinance Model8K / 2.1 GB70
... 2.8 Gemma 2B HQQ 1bit Smashed8K / 1.3 GB50
Note: green Score (e.g. "73.2") means that the model is better than TechxGenus/gemma-1.1-2b-it-AWQ.