Instructions to use steampunque/Voxtral-Mini-3B-2507-MP-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 steampunque/Voxtral-Mini-3B-2507-MP-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 steampunque/Voxtral-Mini-3B-2507-MP-GGUF:Q6_K_H
# Run inference directly in the terminal:
llama cli -hf steampunque/Voxtral-Mini-3B-2507-MP-GGUF:Q6_K_H

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf steampunque/Voxtral-Mini-3B-2507-MP-GGUF:Q6_K_H
# Run inference directly in the terminal:
llama cli -hf steampunque/Voxtral-Mini-3B-2507-MP-GGUF:Q6_K_H

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 steampunque/Voxtral-Mini-3B-2507-MP-GGUF:Q6_K_H
# Run inference directly in the terminal:
./llama-cli -hf steampunque/Voxtral-Mini-3B-2507-MP-GGUF:Q6_K_H

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 steampunque/Voxtral-Mini-3B-2507-MP-GGUF:Q6_K_H
# Run inference directly in the terminal:
./build/bin/llama-cli -hf steampunque/Voxtral-Mini-3B-2507-MP-GGUF:Q6_K_H

Use Docker

docker model run hf.co/steampunque/Voxtral-Mini-3B-2507-MP-GGUF:Q6_K_H

LM Studio
Jan
Ollama
How to use steampunque/Voxtral-Mini-3B-2507-MP-GGUF with Ollama:
```
ollama run hf.co/steampunque/Voxtral-Mini-3B-2507-MP-GGUF:Q6_K_H
```
Unsloth Desktop

How to use steampunque/Voxtral-Mini-3B-2507-MP-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf steampunque/Voxtral-Mini-3B-2507-MP-GGUF:Q6_K_H

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": "steampunque/Voxtral-Mini-3B-2507-MP-GGUF:Q6_K_H"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use steampunque/Voxtral-Mini-3B-2507-MP-GGUF with Docker Model Runner:
```
docker model run hf.co/steampunque/Voxtral-Mini-3B-2507-MP-GGUF:Q6_K_H
```

Lemonade

How to use steampunque/Voxtral-Mini-3B-2507-MP-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull steampunque/Voxtral-Mini-3B-2507-MP-GGUF:Q6_K_H

Run and chat with the model

lemonade run user.Voxtral-Mini-3B-2507-MP-GGUF-Q6_K_H

List all available models

lemonade list

Hermes Agent

How to use steampunque/Voxtral-Mini-3B-2507-MP-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 steampunque/Voxtral-Mini-3B-2507-MP-GGUF:Q6_K_H

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 steampunque/Voxtral-Mini-3B-2507-MP-GGUF:Q6_K_H

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use steampunque/Voxtral-Mini-3B-2507-MP-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf steampunque/Voxtral-Mini-3B-2507-MP-GGUF:Q6_K_H

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 "steampunque/Voxtral-Mini-3B-2507-MP-GGUF:Q6_K_H" \
  --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"

steampunque commited on Feb 18

Commit

6808d13

verified ·

1 Parent(s): 9021f11

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -10,7 +10,7 @@ tags:
 - 6-bit
 ---
-## GGUF hybrid layer quantization of Voxtral-Mini-3B-2512 by mistralai
 Original model: https://huggingface.co/mistralai/Voxtral-Mini-3B-2507
@@ -98,8 +98,8 @@ A full set of audio benchmarks for the model is given here: https://huggingface.
 ## Download the file from below:
 | Link | Type | Size/e9 B | Notes |
 |------|------|-----------|-------|
-| [Voxtral-Mini-3B-2507.Q6_K_H.gguf](https://huggingface.co/steampunque/Voxtral-Mini-3B-2507-Hybrid-GGUF/resolve/main/Voxtral-Mini-3B-2507.Q6_K_H.gguf) | Q6_K_H | 3.2e9 B | ~Q6_K size |
-| [Voxtral-Mini-3B-2507.mmproj.gguf](https://huggingface.co/steampunque/Voxtral-Mini-3B-2507-Hybrid-GGUF/resolve/main/Voxtral-Mini-3B-2517.mmproj.gguf) | F16 | 1.3e9 B | multimedia projector |
 A discussion thread about the hybrid layer quant approach can be found here on the llama.cpp git repository:

 - 6-bit
 ---
+## Mixed Precision GGUF layer quantization of Voxtral-Mini-3B-2512 by mistralai
 Original model: https://huggingface.co/mistralai/Voxtral-Mini-3B-2507
 ## Download the file from below:
 | Link | Type | Size/e9 B | Notes |
 |------|------|-----------|-------|
+| [Voxtral-Mini-3B-2507.Q6_K_H.gguf](https://huggingface.co/steampunque/Voxtral-Mini-3B-2507-MP-GGUF/resolve/main/Voxtral-Mini-3B-2507.Q6_K_H.gguf) | Q6_K_H | 3.2e9 B | ~Q6_K size |
+| [Voxtral-Mini-3B-2507.mmproj.gguf](https://huggingface.co/steampunque/Voxtral-Mini-3B-2507-MP-GGUF/resolve/main/Voxtral-Mini-3B-2517.mmproj.gguf) | F16 | 1.3e9 B | multimedia projector |
 A discussion thread about the hybrid layer quant approach can be found here on the llama.cpp git repository: