LLM EXPLORER 59,420 MODELS INDEXED

Airoboros 33B Gpt4 1 4 SuperHOT 8K GPTQ by TheBloke

By TheBloke · 80 downloads

Airoboros 33B Gpt4 1 4 SuperHOT 8K GPTQ is an open-source language model by TheBloke. Features: 33b LLM, VRAM: 16.9GB, Context: 8K, License: other, Quantized, LLM Explorer Score: 0.12, Arc: 24.7, HellaSwag: 31.2, MMLU: 23.1.

  4-bit   Custom code   Ext 8k   Gptq   Llama   Quantized   Region:us   Safetensors

Airoboros 33B Gpt4 1 4 SuperHOT 8K GPTQ Parameters and Internals

Model Type 
Text Generation
Use Cases 
Areas:
Research
Applications:
AI Development, Chatbots, Text Analysis
Primary Use Cases:
Text generation, Roleplay/chat, Coding tasks
Additional Notes 
Supports multi-line and multi-character conversations. Capable of context-obedient question answering. Format configuration enhances comprehension of commands.
Supported Languages 
English (Full)
Training Details 
Data Sources:
Synthetic data from GPT-4, Rosetta Code Dataset
Methodology:
qLoRA fine-tune
Context Length:
8192
Hardware Used:
4-bit Base Model
Model Architecture:
Quantised Model
Safety Evaluation 
Methodologies:
None specified
Input Output 
Input Format:
BEGININPUT with context metadata and instructions
Accepted Modalities:
Text
Output Format:
Plain text, formatted as specified
Release Notes 
Version:
1.4
Notes:
Increased context size to 8K. Incorporates SuperHOT 8K technique.
LLM NameAiroboros 33B Gpt4 1 4 SuperHOT 8K GPTQ
Repository πŸ€—https://huggingface.co/TheBloke/airoboros-33B-gpt4-1-4-SuperHOT-8K-GPTQ 
Base Model(s)  Panchovix/airoboros-33b-gpt4-1.2-SuperHOT-8k   Panchovix/airoboros-33b-gpt4-1.2-SuperHOT-8k
Model Size33b
Required VRAM16.9 GB
Updated2026-08-06
MaintainerTheBloke
Model Typellama
Model Files  16.9 GB
GPTQ QuantizationYes
Context Length8k
Quantization Typegptq
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 Airoboros 33B Gpt4 1 4 SuperHOT 8K GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
Everyone Coder 33B Base GPTQ16K / 17.4 GB23
WhiteRabbitNeo 33B V1 GPTQ16K / 17.4 GB574
CodeFuse DeepSeek 33B 4bits16K / 18.7 GB710
WizardCoder 33B V1.1 GPTQ16K / 17.4 GB1611
...epseek Coder 33B Instruct GPTQ16K / 17.4 GB26725
Deepseek Coder 33B Base GPTQ16K / 17.4 GB182
Sorceroboros 33B S2a4 Gptq8K / 17.6 GB73
...icuna 33B 1 3 SuperHOT 8K GPTQ8K / 16.9 GB6727
...Combined Data SuperHOT 8K GPTQ8K / 18.1 GB54
...se Alpaca 33B SuperHOT 8K GPTQ8K / 17.4 GB4511