Instructions to use SaisExperiments/Voxtral-3B-But-4B-Text-Only-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SaisExperiments/Voxtral-3B-But-4B-Text-Only-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="SaisExperiments/Voxtral-3B-But-4B-Text-Only-GGUF",
	filename="Voxtral-3B-But-4B-Text-Only-F16.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use SaisExperiments/Voxtral-3B-But-4B-Text-Only-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf SaisExperiments/Voxtral-3B-But-4B-Text-Only-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf SaisExperiments/Voxtral-3B-But-4B-Text-Only-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf SaisExperiments/Voxtral-3B-But-4B-Text-Only-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf SaisExperiments/Voxtral-3B-But-4B-Text-Only-GGUF:F16

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 SaisExperiments/Voxtral-3B-But-4B-Text-Only-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf SaisExperiments/Voxtral-3B-But-4B-Text-Only-GGUF:F16

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 SaisExperiments/Voxtral-3B-But-4B-Text-Only-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf SaisExperiments/Voxtral-3B-But-4B-Text-Only-GGUF:F16

Use Docker

docker model run hf.co/SaisExperiments/Voxtral-3B-But-4B-Text-Only-GGUF:F16

LM Studio
Jan
Ollama
How to use SaisExperiments/Voxtral-3B-But-4B-Text-Only-GGUF with Ollama:
```
ollama run hf.co/SaisExperiments/Voxtral-3B-But-4B-Text-Only-GGUF:F16
```

Unsloth Studio new

How to use SaisExperiments/Voxtral-3B-But-4B-Text-Only-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 SaisExperiments/Voxtral-3B-But-4B-Text-Only-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 SaisExperiments/Voxtral-3B-But-4B-Text-Only-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for SaisExperiments/Voxtral-3B-But-4B-Text-Only-GGUF to start chatting

Pi new

How to use SaisExperiments/Voxtral-3B-But-4B-Text-Only-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf SaisExperiments/Voxtral-3B-But-4B-Text-Only-GGUF:F16

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": "SaisExperiments/Voxtral-3B-But-4B-Text-Only-GGUF:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use SaisExperiments/Voxtral-3B-But-4B-Text-Only-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 SaisExperiments/Voxtral-3B-But-4B-Text-Only-GGUF:F16

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 SaisExperiments/Voxtral-3B-But-4B-Text-Only-GGUF:F16

Run Hermes

hermes

Docker Model Runner
How to use SaisExperiments/Voxtral-3B-But-4B-Text-Only-GGUF with Docker Model Runner:
```
docker model run hf.co/SaisExperiments/Voxtral-3B-But-4B-Text-Only-GGUF:F16
```

Lemonade

How to use SaisExperiments/Voxtral-3B-But-4B-Text-Only-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SaisExperiments/Voxtral-3B-But-4B-Text-Only-GGUF:F16

Run and chat with the model

lemonade run user.Voxtral-3B-But-4B-Text-Only-GGUF-F16

List all available models

lemonade list

mistralai/Voxtral-Mini-3B-2507 with the whisper layers ripped out, mixed with the ministral configs then quantized (with imatrix) :3

Voxtral-3B-But-4B-Text-Only-Q4_0.gguf:

Human: How does your lobotomy feel?

AI: As a machine learning model, I don't have feelings, emotions, or a physical presence, so I don't undergo or experience lobotomies. Lobotomies were a procedure used in the 20th century to treat mental health conditions by cutting into the brain to remove or damage certain parts. They are now considered highly unethical and are no longer practiced.

If you have any specific questions about lobotomies or mental health, I'm here to help! For example, you might want to know:

* What lobotomies are and why they were performed.
* The history of lobotomies and their evolution.
* The effects of lobotomies on mental health and overall well-being.
* The ethical considerations surrounding lobotomies and mental health treatments today.

Please provide more context if you need specific information!

Quantization Type	Bits Per Weight (BPW)	Perplexity (PPL)	Error (+/-)
F16	16.00	7.5143	0.04624
Q8_0	8.50	7.5178	0.04629
Q6_K	6.56	7.5293	0.04648
Q5_K_M	5.71	7.5692	0.04671
IQ4_NL	4.73	7.7711	0.04801
Q4_0	4.72	7.9267	0.04908
IQ4_XS	4.51	7.7913	0.04814

Downloads last month: 50

GGUF

Model size

4B params

Architecture

llama

Hardware compatibility

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW

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

Model tree for SaisExperiments/Voxtral-3B-But-4B-Text-Only-GGUF

Base model

mistralai/Voxtral-Mini-3B-2507

Quantized

(18)

this model