---
tags:
- pruna-ai
- llama-cpp
- gguf-my-repo
base_model: microsoft/Phi-3-mini-128k-instruct
metrics:
- memory_disk
- memory_inference
- inference_latency
- inference_throughput
- inference_CO2_emissions
- inference_energy_consumption
thumbnail: https://assets-global.website-files.com/646b351987a8d8ce158d1940/64ec9e96b4334c0e1ac41504_Logo%20with%20white%20text.svg
---

# suraiy/microsoft-Phi-3-mini-128k-instruct-HQQ-4bit-smashed-Q4_K_M-GGUF
This model was converted to GGUF format from [`PrunaAI/microsoft-Phi-3-mini-128k-instruct-HQQ-4bit-smashed`](https://huggingface.co/PrunaAI/microsoft-Phi-3-mini-128k-instruct-HQQ-4bit-smashed) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/PrunaAI/microsoft-Phi-3-mini-128k-instruct-HQQ-4bit-smashed) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew.
```bash
brew install ggerganov/ggerganov/llama.cpp
```
Invoke the llama.cpp server or the CLI.
CLI:
```bash
llama-cli --hf-repo suraiy/microsoft-Phi-3-mini-128k-instruct-HQQ-4bit-smashed-Q4_K_M-GGUF --model microsoft-phi-3-mini-128k-instruct-hqq-4bit-smashed-q4_k_m.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo suraiy/microsoft-Phi-3-mini-128k-instruct-HQQ-4bit-smashed-Q4_K_M-GGUF --model microsoft-phi-3-mini-128k-instruct-hqq-4bit-smashed-q4_k_m.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
```
git clone https://github.com/ggerganov/llama.cpp && \
cd llama.cpp && \
make && \
./main -m microsoft-phi-3-mini-128k-instruct-hqq-4bit-smashed-q4_k_m.gguf -n 128
```