Instructions to use aimi-models/llm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aimi-models/llm with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="aimi-models/llm",
	filename="Mistral-Small-3.2-24B-Instruct-2506-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use aimi-models/llm with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf aimi-models/llm:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf aimi-models/llm:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf aimi-models/llm:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf aimi-models/llm:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf aimi-models/llm:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf aimi-models/llm:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf aimi-models/llm:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf aimi-models/llm:Q4_K_M

Use Docker

docker model run hf.co/aimi-models/llm:Q4_K_M

LM Studio
Jan
Ollama
How to use aimi-models/llm with Ollama:
```
ollama run hf.co/aimi-models/llm:Q4_K_M
```

Unsloth Studio new

How to use aimi-models/llm with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for aimi-models/llm to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for aimi-models/llm to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for aimi-models/llm to start chatting

Pi new

How to use aimi-models/llm with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf aimi-models/llm:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "llm"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use aimi-models/llm with Docker Model Runner:
```
docker model run hf.co/aimi-models/llm:Q4_K_M
```

Lemonade

How to use aimi-models/llm with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull aimi-models/llm:Q4_K_M

Run and chat with the model

lemonade run user.llm-Q4_K_M

List all available models

lemonade list

LLM Mirror (A.I.M.I)

Mirror of A.I.M.I's default text-LLM GGUFs, re-hosted for stable URLs. Contents unmodified from upstream unsloth/Qwen quantizations.

Used by A.I.M.I's chat engine via llama.cpp. Qwen3-8B is the 16 GB tier default; Mistral Small 3.2 24B is the 24 GB+ tier upgrade.

Files

File	Upstream	Size	Tier
`Qwen3-8B-Q4_K_M.gguf`	Qwen/Qwen3-8B-GGUF	~5.0 GB	16 GB default
`Mistral-Small-3.2-24B-Instruct-2506-Q4_K_M.gguf`	unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF	~14.3 GB	24 GB+ default

Total: ~19 GB.

License

Both models Apache 2.0:

Mistral Small 3.2 24B Instruct: Apache 2.0 from Mistral AI. Unsloth's GGUF re-quantization inherits Apache 2.0.
Qwen3-8B: Apache 2.0 from Alibaba Cloud / Qwen team. GGUF by Qwen team directly.

Redistributed unchanged.

Attribution

Mistral Small 3.2: Mistral AI (2025). Base Apache 2.0 release.
Qwen3-8B: Alibaba Cloud / Qwen team (2025). Base Apache 2.0 release.
GGUF conversions: unsloth (Mistral), Qwen team (Qwen3).

Downloads last month: 32

GGUF

Model size

24B params

Architecture

llama

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support