Instructions to use nif0/Qwen3-VL-32B-Instruct-MiniMax-H3-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 nif0/Qwen3-VL-32B-Instruct-MiniMax-H3-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 nif0/Qwen3-VL-32B-Instruct-MiniMax-H3-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf nif0/Qwen3-VL-32B-Instruct-MiniMax-H3-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf nif0/Qwen3-VL-32B-Instruct-MiniMax-H3-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf nif0/Qwen3-VL-32B-Instruct-MiniMax-H3-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 nif0/Qwen3-VL-32B-Instruct-MiniMax-H3-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf nif0/Qwen3-VL-32B-Instruct-MiniMax-H3-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 nif0/Qwen3-VL-32B-Instruct-MiniMax-H3-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf nif0/Qwen3-VL-32B-Instruct-MiniMax-H3-GGUF:Q4_K_M

Use Docker

docker model run hf.co/nif0/Qwen3-VL-32B-Instruct-MiniMax-H3-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use nif0/Qwen3-VL-32B-Instruct-MiniMax-H3-GGUF with Ollama:
```
ollama run hf.co/nif0/Qwen3-VL-32B-Instruct-MiniMax-H3-GGUF:Q4_K_M
```

Unsloth Studio

How to use nif0/Qwen3-VL-32B-Instruct-MiniMax-H3-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 nif0/Qwen3-VL-32B-Instruct-MiniMax-H3-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 nif0/Qwen3-VL-32B-Instruct-MiniMax-H3-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for nif0/Qwen3-VL-32B-Instruct-MiniMax-H3-GGUF to start chatting

How to use nif0/Qwen3-VL-32B-Instruct-MiniMax-H3-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf nif0/Qwen3-VL-32B-Instruct-MiniMax-H3-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": "nif0/Qwen3-VL-32B-Instruct-MiniMax-H3-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use nif0/Qwen3-VL-32B-Instruct-MiniMax-H3-GGUF with Docker Model Runner:
```
docker model run hf.co/nif0/Qwen3-VL-32B-Instruct-MiniMax-H3-GGUF:Q4_K_M
```

Lemonade

How to use nif0/Qwen3-VL-32B-Instruct-MiniMax-H3-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull nif0/Qwen3-VL-32B-Instruct-MiniMax-H3-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3-VL-32B-Instruct-MiniMax-H3-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use nif0/Qwen3-VL-32B-Instruct-MiniMax-H3-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 nif0/Qwen3-VL-32B-Instruct-MiniMax-H3-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 nif0/Qwen3-VL-32B-Instruct-MiniMax-H3-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use nif0/Qwen3-VL-32B-Instruct-MiniMax-H3-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf nif0/Qwen3-VL-32B-Instruct-MiniMax-H3-GGUF:Q4_K_M

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 "nif0/Qwen3-VL-32B-Instruct-MiniMax-H3-GGUF:Q4_K_M" \
  --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"

Have you compared the speed between fp16 version and gguf version?

by yunming181920 - opened 13 days ago

Discussion

yunming181920

13 days ago

Thank you for your nice work. I found that my 16GB gpu spends lots of time becuase the fp16 model is larger than my vram and the prompts for Minimax H3 are very long. So I wanna know if I directly use the lightest gguf version, will the model as well as the activations always be kept in 16GB vram?

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