gemma-4-26B-A4B-it-speculator.eagle3-F16-GGUF

Description

gemma-4-26B-A4B-it-speculator.eagle3-F16-GGUF is an open-weight text-generation model with roughly 26B parameters published by williamliao on the Hugging Face Hub. It has 99,373 downloads. Runs with llama.cpp.

Categories

• Coding
• Productivity

Tags

• llama.cpp
• eagle3
• speculative-decoding
• speculator
• draft-model
• gemma-4
• gemma
• moe

Capabilities

• Text generation
• Conversational
• GGUF quantised builds
• Library: llama.cpp
• 26B parameters