LLM EXPLORER 62,076 MODELS INDEXED

Platypus2 70B Instruct GGUF by TheBloke

By TheBloke · 505 downloads
HF Repo ↗ Copy URL

Platypus2 70B Instruct GGUF is an open-source language model by TheBloke. Features: 70b LLM, VRAM: 29.3GB, License: cc-by-nc-4.0, Quantized, Instruction-Based, LLM Explorer Score: 0.09.

  Arxiv:2307.09288   Arxiv:2308.07317 Base model:garage-baind/platyp... Base model:quantized:garage-ba... Dataset:garage-baind/open-plat...   Dataset:open-orca/openorca   En   Gguf   Instruct   Llama   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/TheBloke/Platypus2-70B-Instruct-GGUF 

Platypus2 70B Instruct GGUF Parameters and Internals

Model Type 
llama, auto-regressive
Use Cases 
Limitations:
The model may produce inaccurate, biased or other objectionable responses to user prompts.
Considerations:
Before deploying, perform safety testing and tuning tailored to specific applications.
Additional Notes 
The model is suitable for use with text-generation-webui for various AI tasks.
Supported Languages 
English (Proficient)
Training Details 
Data Sources:
garage-bAInd/Open-Platypus
Methodology:
Instruction fine-tuned using LoRA on 8 A100 80GB
Hardware Used:
8 A100 80GB
Model Architecture:
LLaMA 2 transformer
Responsible Ai Considerations 
Accountability:
Developers should perform safety testing and tuning tailored to their specific applications of the model.
Input Output 
Input Format:
Instruction with response format
Accepted Modalities:
text
Output Format:
Textual response
LLM NamePlatypus2 70B Instruct GGUF
Repository 🤗https://huggingface.co/TheBloke/Platypus2-70B-Instruct-GGUF 
Model NamePlatypus2 70B Instruct
Model Creatorgarage-bAInd
Base Model(s)  Platypus2 70B Instruct   garage-bAInd/Platypus2-70B-instruct
Model Size70b
Required VRAM29.3 GB
Updated2026-08-03
MaintainerTheBloke
Model Typellama
Instruction-BasedYes
Model Files  29.3 GB   36.1 GB   33.2 GB   29.9 GB   38.9 GB   41.4 GB   39.1 GB   47.5 GB   48.8 GB   47.5 GB
Supported Languagesen
GGUF QuantizationYes
Quantization Typegguf
Model ArchitectureAutoModel
Licensecc-by-nc-4.0

Best Alternatives to Platypus2 70B Instruct GGUF

Best Alternatives
Context / RAM
Downloads
Likes
CodeLlama 70B Instruct GGUF0K / 25.5 GB137564
Meta Llama 3 70B Instruct GGUF0K / 26.4 GB1334
DAD Model V2 70B Q40K / 42.5 GB130
Swallow 70B Instruct GGUF0K / 29.4 GB14959
Leo Hessianai 70B Chat GGUF0K / 29.3 GB6171
...tablelm Instruct Beta 70B GGUF0K / 29.3 GB133412
Dolphin 2.2 70B GGUF0K / 29.3 GB73217
...e Llama 2 70B Instruct V2 GGUF0K / 29.3 GB9619
Llama 2 70B Orca 200K GGUF0K / 29.3 GB90122
... Distil Llama 3.3 70B Instruct0K / 0.8 GB93
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Platypus2-70B-Instruct-GGUF.