nozdev/ollama

DeepSeek-R1-Distill-Qwen-1.5B GGUF

This repo contains a GGUF version of DeepSeek-R1-Distill-Qwen-1.5B.

• —Quantization: Q5KM (Medium, 5-bit)
• —Architecture: Qwen2.5-Math-1.5B
• —Context Window: Up to 128k tokens

Usage

You can run this model using llama.cpp or other GGUF-compatible tools like LM Studio.