LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

GPT Oss 20B by openai

 »  All LLMs  »  openai  »  GPT Oss 20B   URL Share it on

  7309629   
  Arxiv:2508.10925   8-bit   Autotrain compatible   Conversational   Endpoints compatible   Gpt oss   Mxfp4   Region:us   Safetensors   Sharded   Tensorflow   Vllm
Model Card on HF 🤗: https://huggingface.co/openai/gpt-oss-20b 

GPT Oss 20B Benchmarks

LLME Score: 0.62173
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
GPT Oss 20B (openai/gpt-oss-20b)
🌟 Advertise your project 🚀

GPT Oss 20B Parameters and Internals

LLM NameGPT Oss 20B
Repository 🤗https://huggingface.co/openai/gpt-oss-20b 
Model Size20b
Required VRAM13.8 GB
Updated2025-09-23
Maintaineropenai
Model Typegpt_oss
Model Files  4.8 GB: 0-of-2   4.8 GB: 1-of-2   4.2 GB: 2-of-2
Model ArchitectureGptOssForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.55.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|endoftext|>
Vocabulary Size201088

Quantized Models of the GPT Oss 20B

Model
Likes
Downloads
VRAM
GPT Oss 20B GGUF44721087211 GB
GPT Oss 20B MXFP4 Q8968970012 GB
GPT Oss 20B MLX 8bit4225327622 GB
GPT Oss 20B Unsloth Bnb 4bit2713256612 GB
GPT Oss 20B Bnb 4bit122276940 GB
GPT Oss 20B MXFP4 Q44136611 GB

Best Alternatives to GPT Oss 20B

Best Alternatives
Context / RAM
Downloads
Likes
GPT Oss 20B BF16128K / 41.6 GB11085120
GPT Oss 20B128K / 13.8 GB4187335
Medical Reasoning GPT Oss 20B128K / 12.5 GB342224
GPT Oss 20B Dequantized128K / 41.6 GB41200
GPT OSS Code Reasoning 20B128K / 13.8 GB7116
GPT Oss 20B ShiningValiant3128K / 41.6 GB1716
Codegpt Oss 20B128K / 41.6 GB163
Med GPT Oss 20B128K / 41.6 GB274
...PT OSS 26B Abliterated Preview128K / 51.4 GB134
GPT Oss 20B Offload128K / 41.6 GB181

Rank the GPT Oss 20B 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? 51552 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.
Release v20241124
  Support LLM Explorer