LFM2.5-2.6B-Windows-RTX-CUDA-GGUF

Description

LFM2.5-2.6B-Windows-RTX-CUDA-GGUF is an open-weight text-generation model with roughly 2.6B parameters published by petr567 on the Hugging Face Hub. It has 283 downloads. Runs with llama.cpp.

Categories

• Coding
• Productivity

Tags

• llama.cpp
• lfm2
• lfm2.5
• windows
• cuda
• nvidia
• speculative-decoding
• fast-inference

Capabilities

• Text generation
• Conversational
• GGUF quantised builds
• Library: llama.cpp
• 2.6B parameters