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

Cognitivecomputations Dolphin 2.8 Gemma 2B HQQ 4bit Smashed by PrunaAI

 »  All LLMs  »  PrunaAI  »  Cognitivecomputations Dolphin 2.8 Gemma 2B HQQ 4bit Smashed   URL Share it on

  5   

Cognitivecomputations Dolphin 2.8 Gemma 2B HQQ 4bit Smashed is an open-source language model by PrunaAI. Features: 2b LLM, VRAM: 2.1GB, Context: 8K, Quantized, LLM Explorer Score: 0.14.

  4bit Base model:cognitivecomputatio... Base model:finetune:cognitivec...   Gemma   Pruna-ai   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/PrunaAI/cognitivecomputations-dolphin-2.8-gemma-2b-HQQ-4bit-smashed 

Cognitivecomputations Dolphin 2.8 Gemma 2B HQQ 4bit Smashed Benchmarks

LLME Score: 0.13692
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Cognitivecomputations Dolphin 2.8 Gemma 2B HQQ 4bit Smashed (PrunaAI/cognitivecomputations-dolphin-2.8-gemma-2b-HQQ-4bit-smashed)
🌟 Advertise your project 🚀

Cognitivecomputations Dolphin 2.8 Gemma 2B HQQ 4bit Smashed Parameters and Internals

Model Type 
compressed, quantized, 4-bit
Use Cases 
Areas:
general
Applications:
use-case conditions testing
Additional Notes 
Results may vary depending on specific GPU processes and hardware used.
Training Details 
Data Sources:
WikiText
Methodology:
compressed with hqq
Input Output 
Input Format:
Tokenized input using AutoTokenizer from transformers.
Accepted Modalities:
text
Output Format:
Decoded text output
Performance Tips:
Runs might be affected by cuda overheads in initial executions.
LLM NameCognitivecomputations Dolphin 2.8 Gemma 2B HQQ 4bit Smashed
Repository 🤗https://huggingface.co/PrunaAI/cognitivecomputations-dolphin-2.8-gemma-2b-HQQ-4bit-smashed 
Base Model(s)  cognitivecomputations/dolphin-2.8-gemma-2b   cognitivecomputations/dolphin-2.8-gemma-2b
Model Size2b
Required VRAM2.1 GB
Updated2025-09-23
MaintainerPrunaAI
Model Typegemma
Model Files  2.1 GB
Quantization Type4bit
Model ArchitectureGemmaForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.40.0
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size256000
Torch Data Typefloat16

Best Alternatives to Cognitivecomputations Dolphin 2.8 Gemma 2B HQQ 4bit Smashed

Best Alternatives
Context / RAM
Downloads
Likes
... 2B It Hermes Function Calling8K / 5.1 GB50
Gemma 2B It Bnb 4bit8K / 2.1 GB635420
Gemma 2B Bnb 4bit8K / 2.1 GB602116
Vi Gemma 2B RAG8K / 5.1 GB7213
My AwesomeFinance Model8K / 2.1 GB50
... 2.8 Gemma 2B HQQ 1bit Smashed8K / 1.3 GB50
... 2.8 Gemma 2B HQQ 2bit Smashed8K / 1.6 GB50
Emo AI 3B8K / 5.1 GB51
Jenna V3 QGemma 2B8K / 5.1 GB60
Gemma 2B Sentiment8K / 5.1 GB130
Note: green Score (e.g. "73.2") means that the model is better than PrunaAI/cognitivecomputations-dolphin-2.8-gemma-2b-HQQ-4bit-smashed.

Rank the Cognitivecomputations Dolphin 2.8 Gemma 2B HQQ 4bit Smashed 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? 53972 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer