Instructions to use tensorblock/mlx-community_Mistral-Small-3.2-24B-Instruct-2506-bf16-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tensorblock/mlx-community_Mistral-Small-3.2-24B-Instruct-2506-bf16-GGUF with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("tensorblock/mlx-community_Mistral-Small-3.2-24B-Instruct-2506-bf16-GGUF")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use tensorblock/mlx-community_Mistral-Small-3.2-24B-Instruct-2506-bf16-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 tensorblock/mlx-community_Mistral-Small-3.2-24B-Instruct-2506-bf16-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf tensorblock/mlx-community_Mistral-Small-3.2-24B-Instruct-2506-bf16-GGUF:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf tensorblock/mlx-community_Mistral-Small-3.2-24B-Instruct-2506-bf16-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf tensorblock/mlx-community_Mistral-Small-3.2-24B-Instruct-2506-bf16-GGUF:Q2_K

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 tensorblock/mlx-community_Mistral-Small-3.2-24B-Instruct-2506-bf16-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf tensorblock/mlx-community_Mistral-Small-3.2-24B-Instruct-2506-bf16-GGUF:Q2_K

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 tensorblock/mlx-community_Mistral-Small-3.2-24B-Instruct-2506-bf16-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tensorblock/mlx-community_Mistral-Small-3.2-24B-Instruct-2506-bf16-GGUF:Q2_K

Use Docker

docker model run hf.co/tensorblock/mlx-community_Mistral-Small-3.2-24B-Instruct-2506-bf16-GGUF:Q2_K

LM Studio
Jan

vLLM

How to use tensorblock/mlx-community_Mistral-Small-3.2-24B-Instruct-2506-bf16-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tensorblock/mlx-community_Mistral-Small-3.2-24B-Instruct-2506-bf16-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": "tensorblock/mlx-community_Mistral-Small-3.2-24B-Instruct-2506-bf16-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tensorblock/mlx-community_Mistral-Small-3.2-24B-Instruct-2506-bf16-GGUF:Q2_K

Ollama
How to use tensorblock/mlx-community_Mistral-Small-3.2-24B-Instruct-2506-bf16-GGUF with Ollama:
```
ollama run hf.co/tensorblock/mlx-community_Mistral-Small-3.2-24B-Instruct-2506-bf16-GGUF:Q2_K
```

Unsloth Studio

How to use tensorblock/mlx-community_Mistral-Small-3.2-24B-Instruct-2506-bf16-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 tensorblock/mlx-community_Mistral-Small-3.2-24B-Instruct-2506-bf16-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 tensorblock/mlx-community_Mistral-Small-3.2-24B-Instruct-2506-bf16-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for tensorblock/mlx-community_Mistral-Small-3.2-24B-Instruct-2506-bf16-GGUF to start chatting

Atomic Chat new

MLX LM

How to use tensorblock/mlx-community_Mistral-Small-3.2-24B-Instruct-2506-bf16-GGUF with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "tensorblock/mlx-community_Mistral-Small-3.2-24B-Instruct-2506-bf16-GGUF"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "tensorblock/mlx-community_Mistral-Small-3.2-24B-Instruct-2506-bf16-GGUF"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "tensorblock/mlx-community_Mistral-Small-3.2-24B-Instruct-2506-bf16-GGUF",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Docker Model Runner
How to use tensorblock/mlx-community_Mistral-Small-3.2-24B-Instruct-2506-bf16-GGUF with Docker Model Runner:
```
docker model run hf.co/tensorblock/mlx-community_Mistral-Small-3.2-24B-Instruct-2506-bf16-GGUF:Q2_K
```

Lemonade

How to use tensorblock/mlx-community_Mistral-Small-3.2-24B-Instruct-2506-bf16-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tensorblock/mlx-community_Mistral-Small-3.2-24B-Instruct-2506-bf16-GGUF:Q2_K

Run and chat with the model

lemonade run user.mlx-community_Mistral-Small-3.2-24B-Instruct-2506-bf16-GGUF-Q2_K

List all available models

lemonade list

mlx-community/Mistral-Small-3.2-24B-Instruct-2506-bf16 - GGUF

Join our Discord to learn more about what we're building ↗

This repo contains GGUF format model files for mlx-community/Mistral-Small-3.2-24B-Instruct-2506-bf16.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b5753.

Our projects

Forge

An OpenAI-compatible multi-provider routing layer.
🚀 Try it now! 🚀
Awesome MCP Servers	TensorBlock Studio

A comprehensive collection of Model Context Protocol (MCP) servers.	A lightweight, open, and extensible multi-LLM interaction studio.
👀 See what we built 👀	👀 See what we built 👀

Prompt template

<s>[SYSTEM_PROMPT]{system_prompt}[/SYSTEM_PROMPT][INST]{prompt}[/INST]

Model file specification

Filename	Quant type	File Size	Description
Mistral-Small-3.2-24B-Instruct-2506-bf16-Q2_K.gguf	Q2_K	8.890 GB	smallest, significant quality loss - not recommended for most purposes
Mistral-Small-3.2-24B-Instruct-2506-bf16-Q3_K_S.gguf	Q3_K_S	10.400 GB	very small, high quality loss
Mistral-Small-3.2-24B-Instruct-2506-bf16-Q3_K_M.gguf	Q3_K_M	11.474 GB	very small, high quality loss
Mistral-Small-3.2-24B-Instruct-2506-bf16-Q3_K_L.gguf	Q3_K_L	12.401 GB	small, substantial quality loss
Mistral-Small-3.2-24B-Instruct-2506-bf16-Q4_0.gguf	Q4_0	13.442 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Mistral-Small-3.2-24B-Instruct-2506-bf16-Q4_K_S.gguf	Q4_K_S	13.549 GB	small, greater quality loss
Mistral-Small-3.2-24B-Instruct-2506-bf16-Q4_K_M.gguf	Q4_K_M	14.334 GB	medium, balanced quality - recommended
Mistral-Small-3.2-24B-Instruct-2506-bf16-Q5_0.gguf	Q5_0	16.304 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Mistral-Small-3.2-24B-Instruct-2506-bf16-Q5_K_S.gguf	Q5_K_S	16.304 GB	large, low quality loss - recommended
Mistral-Small-3.2-24B-Instruct-2506-bf16-Q5_K_M.gguf	Q5_K_M	16.764 GB	large, very low quality loss - recommended
Mistral-Small-3.2-24B-Instruct-2506-bf16-Q6_K.gguf	Q6_K	19.346 GB	very large, extremely low quality loss
Mistral-Small-3.2-24B-Instruct-2506-bf16-Q8_0.gguf	Q8_0	25.055 GB	very large, extremely low quality loss - not recommended

Downloading instruction

Command line

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

huggingface-cli download tensorblock/mlx-community_Mistral-Small-3.2-24B-Instruct-2506-bf16-GGUF --include "Mistral-Small-3.2-24B-Instruct-2506-bf16-Q2_K.gguf" --local-dir MY_LOCAL_DIR

If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:

huggingface-cli download tensorblock/mlx-community_Mistral-Small-3.2-24B-Instruct-2506-bf16-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'

Downloads last month: 31

GGUF

Model size

24B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

Model tree for tensorblock/mlx-community_Mistral-Small-3.2-24B-Instruct-2506-bf16-GGUF

Base model

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

Finetuned

mistralai/Mistral-Small-3.2-24B-Instruct-2506

Finetuned

mlx-community/Mistral-Small-3.2-24B-Instruct-2506-bf16

Quantized

(2)

this model