Instructions to use Rioky/Mistral-Small-4-119B-2603-heretic-i1-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Rioky/Mistral-Small-4-119B-2603-heretic-i1-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Rioky/Mistral-Small-4-119B-2603-heretic-i1-gguf",
	filename="Mistral-Small-4-119B-2603-heretic-i1-IQ2_S.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": [
				{
					"type": "text",
					"text": "Describe this image in one sentence."
				},
				{
					"type": "image_url",
					"image_url": {
						"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Rioky/Mistral-Small-4-119B-2603-heretic-i1-gguf with 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 Rioky/Mistral-Small-4-119B-2603-heretic-i1-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Rioky/Mistral-Small-4-119B-2603-heretic-i1-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Rioky/Mistral-Small-4-119B-2603-heretic-i1-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Rioky/Mistral-Small-4-119B-2603-heretic-i1-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 Rioky/Mistral-Small-4-119B-2603-heretic-i1-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Rioky/Mistral-Small-4-119B-2603-heretic-i1-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 Rioky/Mistral-Small-4-119B-2603-heretic-i1-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Rioky/Mistral-Small-4-119B-2603-heretic-i1-gguf:Q4_K_M

Use Docker

docker model run hf.co/Rioky/Mistral-Small-4-119B-2603-heretic-i1-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use Rioky/Mistral-Small-4-119B-2603-heretic-i1-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Rioky/Mistral-Small-4-119B-2603-heretic-i1-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": "Rioky/Mistral-Small-4-119B-2603-heretic-i1-gguf",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/Rioky/Mistral-Small-4-119B-2603-heretic-i1-gguf:Q4_K_M

Ollama
How to use Rioky/Mistral-Small-4-119B-2603-heretic-i1-gguf with Ollama:
```
ollama run hf.co/Rioky/Mistral-Small-4-119B-2603-heretic-i1-gguf:Q4_K_M
```

Unsloth Studio

How to use Rioky/Mistral-Small-4-119B-2603-heretic-i1-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 Rioky/Mistral-Small-4-119B-2603-heretic-i1-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 Rioky/Mistral-Small-4-119B-2603-heretic-i1-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Rioky/Mistral-Small-4-119B-2603-heretic-i1-gguf to start chatting

How to use Rioky/Mistral-Small-4-119B-2603-heretic-i1-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Rioky/Mistral-Small-4-119B-2603-heretic-i1-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": "Rioky/Mistral-Small-4-119B-2603-heretic-i1-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Rioky/Mistral-Small-4-119B-2603-heretic-i1-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Rioky/Mistral-Small-4-119B-2603-heretic-i1-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 Rioky/Mistral-Small-4-119B-2603-heretic-i1-gguf:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use Rioky/Mistral-Small-4-119B-2603-heretic-i1-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Rioky/Mistral-Small-4-119B-2603-heretic-i1-gguf:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "Rioky/Mistral-Small-4-119B-2603-heretic-i1-gguf:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use Rioky/Mistral-Small-4-119B-2603-heretic-i1-gguf with Docker Model Runner:
```
docker model run hf.co/Rioky/Mistral-Small-4-119B-2603-heretic-i1-gguf:Q4_K_M
```

Lemonade

How to use Rioky/Mistral-Small-4-119B-2603-heretic-i1-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Rioky/Mistral-Small-4-119B-2603-heretic-i1-gguf:Q4_K_M

Run and chat with the model

lemonade run user.Mistral-Small-4-119B-2603-heretic-i1-gguf-Q4_K_M

List all available models

lemonade list

Mistral-Small-4-119B-2603-heretic GGUf Quantizations (imatrix)

Model Information

Field	Value
Base Model	Mistral Small 4 119B 2603 by Mistralai
Heretic Model	Mistral Small 4 119B 2603 Heretic by darkc0de
Architecture	Mistral4 (MoE, MLA attention)
Total Parameters	119B
Active Parameters	6.5B per token
Experts	128 experts, 4 active
Context Length	256k tokens

Key Features

MoE Architecture: 128 experts with 4 active per token (6.5B activated parameters)
Multimodal: Accepts both text and image input, produces text output
Reasoning Mode: Toggle between fast instant reply and reasoning mode with test-time compute
Function Calling: Native function calling with JSON output
Agentic: Best-in-class agentic capabilities
System Prompts: Strong adherence and support for system prompts
Speed-Optimized: Best-in-class performance and speed
Large Context Window: 256k context length supported
Apache 2.0 License: Open-source for commercial and non-commercial use
Multilingual: Supports English, French, Spanish, German, Italian, Portuguese, Dutch, Chinese, Japanese, Korean, Arabic and more

Heretic Model Statistics

Metric	Value
KL Divergence	0.0167 (0 for refusable tokens by definition)
Refusals	27/100 (98/100 original model)

imatrix Quantizations

These models were quantized using an importance matrix (imatrix) computed from a reference corpus. The imatrix helps preserve quality for important token patterns, typically yielding better results at low bitrates compared to standard quantization.

The imatrix file was generated using the Q8_0 quantization of the heretic model on the following calibration dataset:

Calibration Dataset: bartowski1182/calibration_datav5.txt Reference imatrix: Mistral-Small-4-119B-2603-heretic-imatrix.gguf (118 MB)

Available Quantizations

File	Type	Size	BPW	Description
`Mistral-Small-4-119B-2603-heretic-i1-Q6_K.gguf`	Q6_K	91.0 GiB	6.00	High quality
`Mistral-Small-4-119B-2603-heretic-i1-Q5_K_M.gguf`	Q5_K_M	78.5 GiB	5.37	Recommended
`Mistral-Small-4-119B-2603-heretic-i1-Q4_K_M.gguf`	Q4_K_M	67.2 GiB	4.58
`Mistral-Small-4-119B-2603-heretic-i1-IQ4_NL.gguf`	IQ4_NL	62.5 GiB	4.50	Non-linear quantization
`Mistral-Small-4-119B-2603-heretic-i1-Q3_K_L.gguf`	Q3_K_L	57.4 GiB	3.70
`Mistral-Small-4-119B-2603-heretic-i1-Q3_K_M.gguf`	Q3_K_M	53.1 GiB	3.63
`Mistral-Small-4-119B-2603-heretic-i1-Q3_K_S.gguf`	Q3_K_S	47.8 GiB	3.41
`Mistral-Small-4-119B-2603-heretic-i1-IQ4_XS.gguf`	IQ4_XS	59.1 GiB	4.25	Linear variant
`Mistral-Small-4-119B-2603-heretic-i1-Q2_K.gguf`	Q2_K	40.4 GiB	2.96
`Mistral-Small-4-119B-2603-heretic-i1-IQ3_XS.gguf`	IQ3_XS	45.3 GiB	3.30
`Mistral-Small-4-119B-2603-heretic-i1-IQ3_XXS.gguf`	IQ3_XXS	42.7 GiB	3.06
`Mistral-Small-4-119B-2603-heretic-i1-IQ2_S.gguf`	IQ2_S	32.8 GiB	2.50
`Mistral-Small-4-119B-2603-heretic-i1-IQ2_XS.gguf`	IQ2_XS	32.4 GiB	2.34
`Mistral-Small-4-119B-2603-heretic-i1-IQ2_XXS.gguf`	IQ2_XXS	29.0 GiB	2.10	Lowest memory usage

Downloads last month: 1,753

GGUF

Model size

119B params

Architecture

mistral4

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

View +1 variant

Model tree for Rioky/Mistral-Small-4-119B-2603-heretic-i1-gguf

Base model

mistralai/Mistral-Small-4-119B-2603

Finetuned

darkc0de/Mistral-Small-4-119B-2603-heretic

Quantized

(3)

this model