How to use from
llama.cpp
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf amiiruu/amiir-ai:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf amiiruu/amiir-ai:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf amiiruu/amiir-ai:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf amiiruu/amiir-ai:Q4_K_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf amiiruu/amiir-ai:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf amiiruu/amiir-ai:Q4_K_M
Use Docker
docker model run hf.co/amiiruu/amiir-ai:Q4_K_M
Quick Links

Amiir AI (amiiruu/amiir-ai)

Created and fine-tuned by Amiir with Unsloth + QLoRA on free Kaggle GPUs.

Run Anywhere in Ollama (No Modelfile Needed)

ollama run hf.co/amiiruu/amiir-ai:Q4_K_M
Downloads last month
70
GGUF
Model size
4B params
Architecture
qwen3
Hardware compatibility
Log In to add your hardware

4-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for amiiruu/amiir-ai

Adapter
(5,868)
this model