Instructions to use bartowski/mistralai_Mistral-Medium-3.5-128B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bartowski/mistralai_Mistral-Medium-3.5-128B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="bartowski/mistralai_Mistral-Medium-3.5-128B-GGUF",
	filename="mistralai_Mistral-Medium-3.5-128B-IQ1_M.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 bartowski/mistralai_Mistral-Medium-3.5-128B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf bartowski/mistralai_Mistral-Medium-3.5-128B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf bartowski/mistralai_Mistral-Medium-3.5-128B-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 bartowski/mistralai_Mistral-Medium-3.5-128B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf bartowski/mistralai_Mistral-Medium-3.5-128B-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 bartowski/mistralai_Mistral-Medium-3.5-128B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf bartowski/mistralai_Mistral-Medium-3.5-128B-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 bartowski/mistralai_Mistral-Medium-3.5-128B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf bartowski/mistralai_Mistral-Medium-3.5-128B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/bartowski/mistralai_Mistral-Medium-3.5-128B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use bartowski/mistralai_Mistral-Medium-3.5-128B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bartowski/mistralai_Mistral-Medium-3.5-128B-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": "bartowski/mistralai_Mistral-Medium-3.5-128B-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/bartowski/mistralai_Mistral-Medium-3.5-128B-GGUF:Q4_K_M

Ollama
How to use bartowski/mistralai_Mistral-Medium-3.5-128B-GGUF with Ollama:
```
ollama run hf.co/bartowski/mistralai_Mistral-Medium-3.5-128B-GGUF:Q4_K_M
```

Unsloth Studio

How to use bartowski/mistralai_Mistral-Medium-3.5-128B-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 bartowski/mistralai_Mistral-Medium-3.5-128B-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 bartowski/mistralai_Mistral-Medium-3.5-128B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for bartowski/mistralai_Mistral-Medium-3.5-128B-GGUF to start chatting

How to use bartowski/mistralai_Mistral-Medium-3.5-128B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf bartowski/mistralai_Mistral-Medium-3.5-128B-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": "bartowski/mistralai_Mistral-Medium-3.5-128B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use bartowski/mistralai_Mistral-Medium-3.5-128B-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 bartowski/mistralai_Mistral-Medium-3.5-128B-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 bartowski/mistralai_Mistral-Medium-3.5-128B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use bartowski/mistralai_Mistral-Medium-3.5-128B-GGUF with Docker Model Runner:
```
docker model run hf.co/bartowski/mistralai_Mistral-Medium-3.5-128B-GGUF:Q4_K_M
```

Lemonade

How to use bartowski/mistralai_Mistral-Medium-3.5-128B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull bartowski/mistralai_Mistral-Medium-3.5-128B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.mistralai_Mistral-Medium-3.5-128B-GGUF-Q4_K_M

List all available models

lemonade list

mmproj file only 50KB

by imweijh - opened Apr 30

Discussion

imweijh

Apr 30

Thank you for everything you've done for the HF community. The mmproj file for this model seems to have an issue with its size—it's only 50 KB.

bartowski

Owner Apr 30

yeah that definitely doesn't look right, funny it didn't get an error when creating it..

arj5n

May 2

Running into this.

bartowski

Owner May 4

had to use the consolidated.safetensors and --mistral-format, something in the regular safetensors is unexpected for convert_hf_to_gguf.py

uploaded fixed mmproj files and will check if there's an obvious fix to upstream for future conversions

bartowski changed discussion status to closed May 4

bartowski

Owner May 4

actually unfortunately even with --mistral-format there seems to be an issue with the default conversion, reuploaded a fix and will have to open a PR

Additionally the f16 format seems to be broken either way so have to use bf16 or f32 if desperate

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment