Qwen3.8-27B-DFlash2-fp8-vllm

Description

Qwen3.8-27B-DFlash2-fp8-vllm is an open-weight text-generation model with roughly 27B parameters published by TechPrototyper on the Hugging Face Hub. It has 1,335 downloads. Runs with transformers.

Categories

• Coding
• Design

Tags

• qwen3
• dflash2
• speculative-decoding
• block-diffusion
• draft-model
• vllm
• fp8
• compressed-tensors

Capabilities

• Text generation
• Library: transformers
• 27B parameters