README.md

metadata

base_model: openai/gpt-oss-120b
license: apache-2.0
model_creator: openai
model_name: gpt-oss-120b
quantized_by: Second State Inc.
pipeline_tag: text-generation
library_name: transformers

---

gpt-oss-120b-GGUF

Original Model

openai/gpt-oss-120b

Run with LlamaEdge

• LlamaEdge version: v0.25.0 and above (0.25.1+ with tool call support)

• Prompt template

  • Prompt type: gpt-oss

  • Prompt string

    <|start|>system<|message|>
    You are ChatGPT, a large language model trained by OpenAI.
    Knowledge cutoff: 2024-06
    Current date: 2025-08-06
    Reasoning: medium
    # Valid channels: analysis, commentary, final. Channel must be included for every message.
    <|end|>
    
    <|start|>user<|message|>Hello!<|end|>
    <|start|>assistant<|channel|>final<|message|>Hi there!<|end|>
    <|start|>user<|message|>What's your favorite color?<|end|>
    <|start|>assistant
    

• Context size: 128000

• Run as LlamaEdge service

  wasmedge --dir .:. --nn-preload default:GGML:AUTO:gpt-oss-120b-MXFP4_MOE.gguf \
    llama-api-server.wasm \
    --model-name gpt-oss-120b \
    --prompt-template gpt-oss \
    --ctx-size 128000
  

Quantized with llama.cpp b6115