DeepSeek-V4-Flash-0731-Pruned-155B-A13B-GGUF

Description

DeepSeek-V4-Flash-0731-Pruned-155B-A13B-GGUF is an open-weight text-generation model with roughly 155B parameters published by takanori-ishikawa on the Hugging Face Hub. It has 2,289 downloads.

Categories

• Coding
• Productivity

Tags

• llama.cpp
• unofficial
• moe
• expert-pruning
• speculative-decoding
• apple-silicon
• text-generation
• imatrix

Capabilities

• Text generation
• Conversational
• GGUF quantised builds
• 155B parameters