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 Experiment26 7B Bnb 4bit Smashed by PrunaAI

 »  All LLMs  »  PrunaAI  »  Cognitivecomputations Dolphin 2.8 Experiment26 7B Bnb 4bit Smashed   URL Share it on

  6   

Cognitivecomputations Dolphin 2.8 Experiment26 7B Bnb 4bit Smashed is an open-source language model by PrunaAI. Features: 7b LLM, VRAM: 4.5GB, Context: 32K, Quantized, LLM Explorer Score: 0.14.

  4-bit   4bit Base model:cognitivecomputatio... Base model:quantized:cognitive...   Bitsandbytes   Mistral   Pruna-ai   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/PrunaAI/cognitivecomputations-dolphin-2.8-experiment26-7b-bnb-4bit-smashed 

Cognitivecomputations Dolphin 2.8 Experiment26 7B Bnb 4bit Smashed Benchmarks

LLME Score: 0.1404
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 Experiment26 7B Bnb 4bit Smashed (PrunaAI/cognitivecomputations-dolphin-2.8-experiment26-7b-bnb-4bit-smashed)
🌟 Advertise your project 🚀

Cognitivecomputations Dolphin 2.8 Experiment26 7B Bnb 4bit Smashed Parameters and Internals

Model Type 
text generation
Additional Notes 
Results mentioning 'first' are obtained after the first run of the model. 'Sync' metrics are obtained by syncing all GPU processes and stopping measurement when all of them are executed. 'Async' metrics stop when the model output can be used by the CPU.
Training Details 
Data Sources:
WikiText
Methodology:
The model is compressed with llm-int8.
Input Output 
Input Format:
Tokenized text inputs.
Accepted Modalities:
text
Output Format:
Generated text.
Performance Tips:
Test efficiency gains directly in your use-cases. Metrics such as 'Sync' and 'Async' could be relevant depending on use-case.
LLM NameCognitivecomputations Dolphin 2.8 Experiment26 7B Bnb 4bit Smashed
Repository 🤗https://huggingface.co/PrunaAI/cognitivecomputations-dolphin-2.8-experiment26-7b-bnb-4bit-smashed 
Base Model(s)  cognitivecomputations/dolphin-2.8-experiment26-7b   cognitivecomputations/dolphin-2.8-experiment26-7b
Model Size7b
Required VRAM4.5 GB
Updated2025-09-23
MaintainerPrunaAI
Model Typemistral
Model Files  4.5 GB
Quantization Type4bit
Model ArchitectureMistralForCausalLM
Context Length32768
Model Max Length32768
Transformers Version4.40.0
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32002
Torch Data Typefloat16

Best Alternatives to Cognitivecomputations Dolphin 2.8 Experiment26 7B Bnb 4bit Smashed

Best Alternatives
Context / RAM
Downloads
Likes
...t 3.5 0106 128K 4.0bpw H6 EXL2128K / 3.9 GB11
...t 3.5 0106 128K 8.0bpw H8 EXL2128K / 7.4 GB11
Mistral 7B V0.3 Bnb 4bit32K / 4.1 GB35143322
Mistral 7B Instruct V0.2 Fp1632K / 14.4 GB260
Mistral 7B Instruct V0.2 4bit32K / 4.3 GB1331
...tral 7B Instruct V0.3 Bnb 4bit32K / 4.1 GB3043728
Mistral 7B Instruct V0.2 8bit32K / 7.6 GB41
...tral 7B Instruct V0.2 Bnb 4bit32K / 4.1 GB1256736
Mixtral V0.3 Full 16bit32K / 14.5 GB60
Mistral 7B Instruct V0.3 4bit32K / 4.1 GB250538
Note: green Score (e.g. "73.2") means that the model is better than PrunaAI/cognitivecomputations-dolphin-2.8-experiment26-7b-bnb-4bit-smashed.

Rank the Cognitivecomputations Dolphin 2.8 Experiment26 7B Bnb 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? 52721 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