Instructions to use NexesQuants/mistral-small-3.1-24b-instruct-2503-iMat-IKLQ-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NexesQuants/mistral-small-3.1-24b-instruct-2503-iMat-IKLQ-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="NexesQuants/mistral-small-3.1-24b-instruct-2503-iMat-IKLQ-GGUF",
	filename="mistral-small-3.1-24b-instruct-2503-bf16.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use NexesQuants/mistral-small-3.1-24b-instruct-2503-iMat-IKLQ-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf NexesQuants/mistral-small-3.1-24b-instruct-2503-iMat-IKLQ-GGUF:BF16
# Run inference directly in the terminal:
llama-cli -hf NexesQuants/mistral-small-3.1-24b-instruct-2503-iMat-IKLQ-GGUF:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf NexesQuants/mistral-small-3.1-24b-instruct-2503-iMat-IKLQ-GGUF:BF16
# Run inference directly in the terminal:
llama-cli -hf NexesQuants/mistral-small-3.1-24b-instruct-2503-iMat-IKLQ-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 NexesQuants/mistral-small-3.1-24b-instruct-2503-iMat-IKLQ-GGUF:BF16
# Run inference directly in the terminal:
./llama-cli -hf NexesQuants/mistral-small-3.1-24b-instruct-2503-iMat-IKLQ-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 NexesQuants/mistral-small-3.1-24b-instruct-2503-iMat-IKLQ-GGUF:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf NexesQuants/mistral-small-3.1-24b-instruct-2503-iMat-IKLQ-GGUF:BF16

Use Docker

docker model run hf.co/NexesQuants/mistral-small-3.1-24b-instruct-2503-iMat-IKLQ-GGUF:BF16

LM Studio
Jan
Ollama
How to use NexesQuants/mistral-small-3.1-24b-instruct-2503-iMat-IKLQ-GGUF with Ollama:
```
ollama run hf.co/NexesQuants/mistral-small-3.1-24b-instruct-2503-iMat-IKLQ-GGUF:BF16
```

Unsloth Studio

How to use NexesQuants/mistral-small-3.1-24b-instruct-2503-iMat-IKLQ-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 NexesQuants/mistral-small-3.1-24b-instruct-2503-iMat-IKLQ-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 NexesQuants/mistral-small-3.1-24b-instruct-2503-iMat-IKLQ-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for NexesQuants/mistral-small-3.1-24b-instruct-2503-iMat-IKLQ-GGUF to start chatting

Docker Model Runner
How to use NexesQuants/mistral-small-3.1-24b-instruct-2503-iMat-IKLQ-GGUF with Docker Model Runner:
```
docker model run hf.co/NexesQuants/mistral-small-3.1-24b-instruct-2503-iMat-IKLQ-GGUF:BF16
```

Lemonade

How to use NexesQuants/mistral-small-3.1-24b-instruct-2503-iMat-IKLQ-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull NexesQuants/mistral-small-3.1-24b-instruct-2503-iMat-IKLQ-GGUF:BF16

Run and chat with the model

lemonade run user.mistral-small-3.1-24b-instruct-2503-iMat-IKLQ-GGUF-BF16

List all available models

lemonade list

About

IQ2_KS, IQ4_KS, IQ5_KS are Gen 2 IQ_K Quants from Ikawrakow. They are faster (PP for sure, TG maybe) than the gen 1 IK_Quants (IQ2_K to IQ6_K). They'll work with my last release of Croco.Cpp.

https://github.com/Nexesenex/croco.cpp/releases/tag/v1.92055_b5145_RM1.102

And of course on IK_Llama.cpp

Cuda Pascal or more recent GPU needed, I didn't adapt or compile for anything else.

Downloads last month: 42

GGUF

Model size

24B params

Architecture

llama

Hardware compatibility

2-bit

16-bit

Inference Providers NEW

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

Model tree for NexesQuants/mistral-small-3.1-24b-instruct-2503-iMat-IKLQ-GGUF

Base model

mistralai/Mistral-Small-3.1-24B-Base-2503

Finetuned

mistralai/Mistral-Small-3.1-24B-Instruct-2503

Quantized

(60)

this model