DeepSeek-V4-Flash-0731-IQ2XXS-Q2K-EM-GGUF

Description

DeepSeek-V4-Flash-0731-IQ2XXS-Q2K-EM-GGUF is an open-weight text-generation model published by SpeederX on the Hugging Face Hub. It has 245 downloads. Runs with gguf.

Categories

• Productivity

Tags

• quantized
• deepseek-v4
• deepseek-v4-flash
• moe
• iq2_xxs
• q2_k
• imatrix
• siliang-engine

Capabilities

• Text generation
• Conversational
• GGUF quantised builds
• Library: gguf