Instructions to use AlexanderKyng/Mistral-Small-119B-2603-ik-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use AlexanderKyng/Mistral-Small-119B-2603-ik-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 AlexanderKyng/Mistral-Small-119B-2603-ik-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf AlexanderKyng/Mistral-Small-119B-2603-ik-GGUF:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf AlexanderKyng/Mistral-Small-119B-2603-ik-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf AlexanderKyng/Mistral-Small-119B-2603-ik-GGUF:BF16

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 AlexanderKyng/Mistral-Small-119B-2603-ik-GGUF:BF16
# Run inference directly in the terminal:
./llama-cli -hf AlexanderKyng/Mistral-Small-119B-2603-ik-GGUF:BF16

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 AlexanderKyng/Mistral-Small-119B-2603-ik-GGUF:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AlexanderKyng/Mistral-Small-119B-2603-ik-GGUF:BF16

Use Docker

docker model run hf.co/AlexanderKyng/Mistral-Small-119B-2603-ik-GGUF:BF16

LM Studio
Jan

vLLM

How to use AlexanderKyng/Mistral-Small-119B-2603-ik-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AlexanderKyng/Mistral-Small-119B-2603-ik-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": "AlexanderKyng/Mistral-Small-119B-2603-ik-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AlexanderKyng/Mistral-Small-119B-2603-ik-GGUF:BF16

Ollama
How to use AlexanderKyng/Mistral-Small-119B-2603-ik-GGUF with Ollama:
```
ollama run hf.co/AlexanderKyng/Mistral-Small-119B-2603-ik-GGUF:BF16
```
Unsloth Desktop

How to use AlexanderKyng/Mistral-Small-119B-2603-ik-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AlexanderKyng/Mistral-Small-119B-2603-ik-GGUF:BF16

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "AlexanderKyng/Mistral-Small-119B-2603-ik-GGUF:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use AlexanderKyng/Mistral-Small-119B-2603-ik-GGUF with Docker Model Runner:
```
docker model run hf.co/AlexanderKyng/Mistral-Small-119B-2603-ik-GGUF:BF16
```

Lemonade

How to use AlexanderKyng/Mistral-Small-119B-2603-ik-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AlexanderKyng/Mistral-Small-119B-2603-ik-GGUF:BF16

Run and chat with the model

lemonade run user.Mistral-Small-119B-2603-ik-GGUF-BF16

List all available models

lemonade list

Hermes Agent

How to use AlexanderKyng/Mistral-Small-119B-2603-ik-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 AlexanderKyng/Mistral-Small-119B-2603-ik-GGUF:BF16

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 AlexanderKyng/Mistral-Small-119B-2603-ik-GGUF:BF16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use AlexanderKyng/Mistral-Small-119B-2603-ik-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AlexanderKyng/Mistral-Small-119B-2603-ik-GGUF:BF16

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 "AlexanderKyng/Mistral-Small-119B-2603-ik-GGUF:BF16" \
  --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"

Mistral-Small-4-119B-2603 GGUF (ik_llama)

This repository provides ik_llama optimized GGUF quantizations for the mistralai/Mistral-Small-4-119B-2603 model.

Optimization and Importance Matrix

These files were generated using the ik_llama.cpp fork, which offers row interleaved formats (R4) specifically designed to minimize degradation in MoE architectures. I send my biggest thanks to the author ikawrakow for developing and maintaining this tool.

To maximize precision, an importance matrix (iMatrix) was computed prior to quantization. This calculation was performed on a RunPod infrastructure equipped with 3 NVIDIA A100 80GB accelerators, ingesting the calibration_data_v5_rc.txt dataset provided by tristandruyen.

Perplexity Scores

All tests were performed on the wikitext-2 dataset using a context window of 1024 tokens and a batch size of 512.

Model Format	Perplexity (PPL)	Size (GiB)	Bits per Weight (BPW)
BF16 (Unsloth Base)	5.3035	221.64	16.00
IQ5_K_R4 (ik_llama)	5.3431	82	5.51
UD_Q4_K_S (Unsloth)	5.3883	69.30	~ 4.50
IQ4_K_R4 (ik_llama)	5.4242	67.2	4.31

Vision and Multimodality Note

This model features vision capabilities. You may find the original model's .mmproj file in the "Files and versions" tab.

Credits

Original model: mistralai/Mistral-Small-4-119B-2603

================== Original Description ==================

Mistral Small 4 is a powerful hybrid model capable of acting as both a general instruction model and a reasoning model. It unifies the capabilities of three different model families—Instruct, Reasoning (previously called Magistral), and Devstral—into a single, unified model.

With its multimodal capabilities, efficient architecture, and flexible mode switching, it is a powerful general-purpose model for any task. In a latency-optimized setup, Mistral Small 4 achieves a 40% reduction in end-to-end completion time, and in a throughput-optimized setup, it handles 3x more requests per second compared to Mistral Small 3.

To further improve efficiency you can either take advantages of:

Speculative decoding thanks to our trained eagle head mistralai/Mistral-Small-4-119B-2603-eagle.
4 bit float precision quantization thanks to our NVFP4 checkpoint mistralai/Mistral-Small-4-119B-2603-NVFP4.

Key Features

Mistral Small 4 includes the following architectural choices:

MoE: 128 experts, 4 active.
119B parameters, with 6.5B activated per token.
256k context length.
Multimodal input: Accepts both text and image input, with text output.
Instruct and Reasoning functionalities with function calls (reasoning effort configurable per request).

Mistral Small 4 offers the following capabilities:

Reasoning Mode: Toggle between fast instant reply mode and reasoning mode, boosting performance with test-time compute when requested.
Vision: Analyzes images and provides insights based on visual content, in addition to text.
Multilingual: Supports dozens of languages, including English, French, Spanish, German, Italian, Portuguese, Dutch, Chinese, Japanese, Korean, and Arabic.
System Prompt: Strong adherence and support for system prompts.
Agentic: Best-in-class agentic capabilities with native function calling and JSON output.
Speed-Optimized: Delivers best-in-class performance and speed.
Apache 2.0 License: Open-source license for both commercial and non-commercial use.
Large Context Window: Supports a 256k context window.

Recommended Settings

Reasoning Effort:
- 'none' → Do not use reasoning
- 'high' → Use reasoning (recommended for complex prompts) Use reasoning_effort="high" for complex tasks
Temperature: 0.7 for reasoning_effort="high". Temp between 0.0 and 0.7 for reasoning_effort="none" depending on task.

Use Cases

Mistral Small 4 is designed for general chat assistants, coding, agentic tasks, and reasoning tasks (with reasoning mode toggled). Its multimodal capabilities also enable document and image understanding for data extraction and analysis.

Its capabilities are ideal for:

Developers interested in coding and agentic capabilities for SWE automation and codebase exploration.
Enterprises seeking general chat assistants, agents, and document understanding.
Researchers leveraging its math and research capabilities.

Mistral Small 4 is also well-suited for customization and fine-tuning for more specialized tasks.

Examples

General chat assistant
Document parsing and extraction
Coding agent
Research assistant
Customization & fine-tuning
And more...

Benchmarks

Comparison with internal models

Depending on your tasks you can trigger reasoning thanks to the support of the per-request parameter reasoning_effort. Set it to:

reasoning_effort="none": Fast, lightweight responses for everyday tasks, equivalent to the same chat style of mistralai/Mistral-Small-3.2-24B-Instruct-2506.
reasoning_effort="high": Deep, step-by-step reasoning for complex problems, with equivalent verbosity to previous Magistral models such as mistralai/Magistral-Small-2509.

Comparing Reasoning Models

Comparison with other models

Mistral Small 4 with reasoning achieves competitive scores, matching or surpassing GPT-OSS 120B across all three benchmarks while generating significantly shorter outputs. On AA LCR, Mistral Small 4 scores 0.72 with just 1.6K characters, whereas Qwen models require 3.5-4x more output (5.8-6.1K) for comparable performance. On LiveCodeBench, Mistral Small 4 outperforms GPT-OSS 120B while producing 20% less output. This efficiency reduces latency, inference costs, and improves user experience.

Usage

You can find Mistral Small 4 support on multiple libraries for inference and fine-tuning. We here thank everyone contributors and maintainers that helped us making it happen.

License

This model is licensed under the Apache 2.0 License.

You must not use this model in a manner that infringes, misappropriates, or violates any third party’s rights, including intellectual property rights.

Downloads last month: 114

GGUF

Model size

119B params

Architecture

mistral4

Hardware compatibility

Model tree for AlexanderKyng/Mistral-Small-119B-2603-ik-GGUF

Base model

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

Quantized

(35)

this model

AlexanderKyng
/

Mistral-Small-119B-2603-ik-GGUF

Mistral-Small-4-119B-2603 GGUF (ik_llama)

Optimization and Importance Matrix

Perplexity Scores

Vision and Multimodality Note

Credits

================== Original Description ==================

Key Features

Recommended Settings

Use Cases

Examples

Benchmarks

Comparison with internal models

Comparing Reasoning Models

Comparison with other models

Usage

License

Model tree for AlexanderKyng/Mistral-Small-119B-2603-ik-GGUF

Dataset used to train AlexanderKyng/Mistral-Small-119B-2603-ik-GGUF