---
license: llama3.1
---
## DeepSeek-R1-Distill-Llama-8B GGUF Q4_K_M model file

``` bash
python llama.cpp/convert_hf_to_gguf.py DeepSeek-R1-Distill-Llama-8B --outfile deepseek-r1-distill-llama-8b.gguf
./llama-quantize deepseek-r1-distill-llama-8b.gguf deepseek-r1-distill-llama-8b-q4_k_m.gguf Q4_K_M
```