# Multi-quantization support
Qwen2.5 1.5B Instruct GGUF
The GGUF format file of the Qwen2.5-1.5B-Instruct model, suitable for text generation tasks.
Large Language Model
Q
MaziyarPanahi
183.11k
6
Fiction.live Kimiko V2 70B GGUF
Openrail
Fiction Live Kimiko V2 70B is a large language model based on the Llama 2 architecture, offering multiple quantization formats suitable for different inference scenarios.
Large Language Model
Transformers English

F
TheBloke
868
13
Featured Recommended AI Models