gpt-oss-120b-DFlash

Description

gpt-oss-120b-DFlash is an open-weight text-generation model with roughly 120B parameters published by z-lab on the Hugging Face Hub. It has 3,772 downloads. Runs with transformers.

Categories

• Coding

Tags

• qwen3
• feature-extraction
• dflash
• speculative-decoding
• diffusion
• efficiency
• flash-decoding
• diffusion-language-model

Capabilities

• Text generation
• Library: transformers
• 120B parameters