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

GPlatty 30B SuperHOT 8K Fp16 by TheBloke

 »  All LLMs  »  TheBloke  »  GPlatty 30B SuperHOT 8K Fp16   URL Share it on

  978   

GPlatty 30B SuperHOT 8K Fp16 is an open-source language model by TheBloke. Features: 30b LLM, VRAM: 65.2GB, Context: 8K, License: other, Quantized, LLM Explorer Score: 0.09.

  Arxiv:2302.13971   Custom code   Ext 8k   Fp16   Llama   Pytorch   Quantized   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/TheBloke/GPlatty-30B-SuperHOT-8K-fp16 

GPlatty 30B SuperHOT 8K Fp16 Benchmarks

LLME Score: 0.09086
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
GPlatty 30B SuperHOT 8K Fp16 (TheBloke/GPlatty-30B-SuperHOT-8K-fp16)
🌟 Advertise your project 🚀

GPlatty 30B SuperHOT 8K Fp16 Parameters and Internals

Model Type 
auto-regressive language model
Use Cases 
Areas:
research, commercial applications
Applications:
text generation, question answering
Primary Use Cases:
extendable context generation, language model evaluation
Limitations:
may contain offensive, harmful, and biased content
Considerations:
Chat responses from this model should not be considered as the ultimate source of truth.
Additional Notes 
This model represents a merge of two prominent models, Platypus-30B and Gpt4-alpaca-lora-30b; uses novel techniques like trust_remote_code=True for leveraging extended context.
Supported Languages 
English (Advanced)
Training Details 
Context Length:
8192
Hardware Used:
A100 80GB GPU
Model Architecture:
LLaMA transformer architecture
Safety Evaluation 
Methodologies:
section 5.1 of the LLaMA paper
Risk Categories:
offensive, harmful, biased content
Ethical Considerations:
We have not performed any studies to determine how fine-tuning on the aforementioned datasets affect the model's behavior and toxicity.
Input Output 
Input Format:
PyTorch format, sequence length up to 8192.
Accepted Modalities:
text
Output Format:
PyTorch output for text generation.
Performance Tips:
Config max_position_embeddings can be set to 4096 for smaller sequence length during inference.
LLM NameGPlatty 30B SuperHOT 8K Fp16
Repository 🤗https://huggingface.co/TheBloke/GPlatty-30B-SuperHOT-8K-fp16 
Model Size30b
Required VRAM65.2 GB
Updated2026-04-03
MaintainerTheBloke
Model Typellama
Model Files  9.8 GB: 1-of-7   10.0 GB: 2-of-7   9.9 GB: 3-of-7   9.9 GB: 4-of-7   9.9 GB: 5-of-7   10.0 GB: 6-of-7   5.7 GB: 7-of-7
Context Length8k
Quantization Typefp16
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length8192
Model Max Length8192
Transformers Version4.30.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to GPlatty 30B SuperHOT 8K Fp16

Best Alternatives
Context / RAM
Downloads
Likes
Tenebra 30B Alpha01 FP1616K / 65 GB18339
Tenebra 30B Alpha01 4BIT16K / 19.4 GB651
...nebra 30B Alpha01 EXL2 2 80bpw16K / 11.9 GB31
Tenebra 30B Alpha01 EXL2 3bpw16K / 12.7 GB60
...nebra 30B Alpha01 EXL2 2 50bpw16K / 10.7 GB50
Tenebra 30B Alpha01 3BIT16K / 12.9 GB60
... 30B Supercot SuperHOT 8K Fp168K / 65.2 GB11734
Platypus 30B SuperHOT 8K Fp168K / 65.2 GB12482
Tulu 30B Fp162K / 65.2 GB19285
WizardLM 30B Fp162K / 65.2 GB191110
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/GPlatty-30B-SuperHOT-8K-fp16.

Rank the GPlatty 30B SuperHOT 8K Fp16 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