DeepSeek-V4-Flash-IQ2XXS-TM64-Q4KAttention-v1

Description

DeepSeek-V4-Flash-IQ2XXS-TM64-Q4KAttention-v1 is an open-weight text-generation model published by erayyapagci on the Hugging Face Hub. It has 835 downloads. Runs with llama.cpp.

Categories

• Coding
• Productivity

Tags

• llama.cpp
• llama-cpp
• deepseek-v4
• quantized
• imatrix
• vulkan
• amd
• strix-halo

Capabilities

• Text generation
• Conversational
• GGUF quantised builds
• Library: llama.cpp