Instructions to use CelesteImperia/Mistral-Nemo-Instruct-Platinum-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CelesteImperia/Mistral-Nemo-Instruct-Platinum-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="CelesteImperia/Mistral-Nemo-Instruct-Platinum-GGUF",
	filename="Mistral-Nemo-Instruct-Platinum-F16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use CelesteImperia/Mistral-Nemo-Instruct-Platinum-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf CelesteImperia/Mistral-Nemo-Instruct-Platinum-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf CelesteImperia/Mistral-Nemo-Instruct-Platinum-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf CelesteImperia/Mistral-Nemo-Instruct-Platinum-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf CelesteImperia/Mistral-Nemo-Instruct-Platinum-GGUF: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 CelesteImperia/Mistral-Nemo-Instruct-Platinum-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf CelesteImperia/Mistral-Nemo-Instruct-Platinum-GGUF: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 CelesteImperia/Mistral-Nemo-Instruct-Platinum-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf CelesteImperia/Mistral-Nemo-Instruct-Platinum-GGUF:Q4_K_M

Use Docker

docker model run hf.co/CelesteImperia/Mistral-Nemo-Instruct-Platinum-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use CelesteImperia/Mistral-Nemo-Instruct-Platinum-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CelesteImperia/Mistral-Nemo-Instruct-Platinum-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CelesteImperia/Mistral-Nemo-Instruct-Platinum-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CelesteImperia/Mistral-Nemo-Instruct-Platinum-GGUF:Q4_K_M

Ollama
How to use CelesteImperia/Mistral-Nemo-Instruct-Platinum-GGUF with Ollama:
```
ollama run hf.co/CelesteImperia/Mistral-Nemo-Instruct-Platinum-GGUF:Q4_K_M
```

Unsloth Studio new

How to use CelesteImperia/Mistral-Nemo-Instruct-Platinum-GGUF 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 CelesteImperia/Mistral-Nemo-Instruct-Platinum-GGUF 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 CelesteImperia/Mistral-Nemo-Instruct-Platinum-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for CelesteImperia/Mistral-Nemo-Instruct-Platinum-GGUF to start chatting

Pi new

How to use CelesteImperia/Mistral-Nemo-Instruct-Platinum-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf CelesteImperia/Mistral-Nemo-Instruct-Platinum-GGUF: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": "CelesteImperia/Mistral-Nemo-Instruct-Platinum-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use CelesteImperia/Mistral-Nemo-Instruct-Platinum-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf CelesteImperia/Mistral-Nemo-Instruct-Platinum-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default CelesteImperia/Mistral-Nemo-Instruct-Platinum-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use CelesteImperia/Mistral-Nemo-Instruct-Platinum-GGUF with Docker Model Runner:
```
docker model run hf.co/CelesteImperia/Mistral-Nemo-Instruct-Platinum-GGUF:Q4_K_M
```

Lemonade

How to use CelesteImperia/Mistral-Nemo-Instruct-Platinum-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull CelesteImperia/Mistral-Nemo-Instruct-Platinum-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Mistral-Nemo-Instruct-Platinum-GGUF-Q4_K_M

List all available models

lemonade list

Mistral-Nemo-12B-Instruct-v1-GGUF (Platinum Series)

This repository contains the Platinum Series universal GGUF release of Mistral-Nemo-12B-Instruct-v1. This collection provides multiple quantization levels optimized for high-performance reasoning and creative applications, bridging the gap between small and large-scale language models.

📦 Available Files & Quantization Details

File Name	Quantization	Size	Accuracy	Recommended For
Mistral-Nemo-12B-Instruct-Platinum-F16.gguf	FP16	~24.5 GB	100%	Master Reference / Benchmarking
Mistral-Nemo-12B-Instruct-Platinum-Q8_0.gguf	Q8_0	~13.0 GB	99.9%	Platinum Reference / High-Fidelity
Mistral-Nemo-12B-Instruct-Platinum-Q6_K.gguf	Q6_K	~10.0 GB	99.8%	High-End GPU / Complex Logic
Mistral-Nemo-12B-Instruct-Platinum-Q5_K_M.gguf	Q5_K_M	~8.7 GB	99.6%	Balanced Performance
Mistral-Nemo-12B-Instruct-Platinum-Q4_K_M.gguf	Q4_K_M	~7.4 GB	99.2%	Efficiency / Mid-Range VRAM

🐍 Python Inference (llama-cpp-python)

To run these engines using Python:

from llama_cpp import Llama

llm = Llama(
    model_path="Mistral-Nemo-12B-Instruct-Platinum-Q8_0.gguf",
    n_gpu_layers=-1, # Target all layers to NVIDIA/Apple GPU
    n_ctx=8192
)

output = llm("Discuss the impact of the Mistral-Nemo architecture.", max_tokens=200)
print(output["choices"][0]["text"])

💻 For C# / .NET Users (LLamaSharp)

This collection is fully compatible with .NET applications via the LLamaSharp library.

using LLama.Common;
using LLama;

var parameters = new ModelParams("Mistral-Nemo-12B-Instruct-Platinum-Q8_0.gguf") {
    ContextSize = 8192,
    GpuLayerCount = 40 
};

using var model = LLamaWeights.LoadFromFile(parameters);
using var context = model.CreateContext(parameters);
var executor = new InteractiveExecutor(context);

Console.WriteLine("Universal Logic Engine Active.");

🏗️ Technical Details

Optimization Tool: llama.cpp (CUDA-accelerated)
Architecture: Mistral Nemo (12B)
Hardware Validation: Dual-GPU (RTX 3090 + RTX A4000)

☕ Support the Forge

Maintaining high-capacity workstations for model conversion requires hardware investment. If these tools power your industrial workflows or local research, please consider supporting the development:

Platform	Support Link
Global & India	Support via Razorpay

Scan to support via UPI (India Only):

Connect with the architect: Abhishek Jaiswal on LinkedIn

Downloads last month: 65

GGUF

Model size

12B params

Architecture

llama

Hardware compatibility

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for CelesteImperia/Mistral-Nemo-Instruct-Platinum-GGUF

Base model

mistralai/Mistral-Nemo-Base-2407

Finetuned

mistralai/Mistral-Nemo-Instruct-2407

Quantized

(174)

this model