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

LLama 3 Mega Dolphin 2.9.1 120B GGUF by DarqueDante

 »  All LLMs  »  DarqueDante  »  LLama 3 Mega Dolphin 2.9.1 120B GGUF   URL Share it on

  34   

LLama 3 Mega Dolphin 2.9.1 120B GGUF is an open-source language model by DarqueDante. Features: 70b LLM, VRAM: 18.4GB, Context: 8K, Quantized, Merged, LLM Explorer Score: 0.14.

  Merged Model Base model:dphn/dolphin-2.9.1-... Base model:quantized:dphn/dolp...   Conversational Dataset:abacusai/systemchat-1.... Dataset:cognitivecomputations/... Dataset:cognitivecomputations/... Dataset:cognitivecomputations/... Dataset:huggingfaceh4/ultracha...   Dataset:internlm/agent-flan Dataset:locutusque/function-ca... Dataset:m-a-p/codefeedback-fil... Dataset:microsoft/orca-math-wo...   Dataset:teknium/openhermes-2.5   En   Endpoints compatible   Gguf   Llama   Q6   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/DarqueDante/LLama-3-Mega-Dolphin-2.9.1-120b_GGUF 

LLama 3 Mega Dolphin 2.9.1 120b GGUF Benchmarks

LLME Score: 0.13674
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
LLama 3 Mega Dolphin 2.9.1 120B GGUF (DarqueDante/LLama-3-Mega-Dolphin-2.9.1-120b_GGUF)
🌟 Advertise your project 🚀

LLama 3 Mega Dolphin 2.9.1 120B GGUF Parameters and Internals

Supported Languages 
en (unknown)
Input Output 
Input Format:
ChatML prompt template
LLM NameLLama 3 Mega Dolphin 2.9.1 120b GGUF
Repository 🤗https://huggingface.co/DarqueDante/LLama-3-Mega-Dolphin-2.9.1-120b_GGUF 
Base Model(s)  cognitivecomputations/dolphin-2.9.1-llama-3-70b   cognitivecomputations/dolphin-2.9.1-llama-3-70b
Merged ModelYes
Model Size70b
Required VRAM18.4 GB
Updated2026-03-30
MaintainerDarqueDante
Model Typellama
Model Files  21.8 GB: 1-of-5   20.0 GB: 2-of-5   19.9 GB: 3-of-5   19.9 GB: 4-of-5   18.4 GB: 5-of-5
Supported Languagesen
GGUF QuantizationYes
Quantization Typegguf|q6
Model ArchitectureLlamaForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.41.0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|end_of_text|>
Vocabulary Size128258
Torch Data Typefloat16

Best Alternatives to LLama 3 Mega Dolphin 2.9.1 120B GGUF

Best Alternatives
Context / RAM
Downloads
Likes
...Seek R1 Distill Llama 70B GGUF128K / 15.9 GB18113110
Llama 3.3 70B Instruct GGUF128K / 15.9 GB19563103
R1 1776 Distill Llama 70B GGUF128K / 26.4 GB22324
Reflection Llama 3.1 70B Bf16128K / 141.9 GB2836
Reflection Llama 3.1 70B GGUF128K / 26.4 GB686
...Horizon AI Korean Advanced 70B128K / 141.9 GB560
Midnight Miqu 70B V1.0 GGUF31K / 29.9 GB1354
...qu 1 70B 24GB VRAM IQ2 XS SOTA31K / 20.3 GB330
...ma3 70B Chinese Chat GGUF 4bit8K / 40 GB36618
Llama 3 70B Quantised8K / 48.7 GB242
Note: green Score (e.g. "73.2") means that the model is better than DarqueDante/LLama-3-Mega-Dolphin-2.9.1-120b_GGUF.

Rank the LLama 3 Mega Dolphin 2.9.1 120B GGUF 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