Instructions to use DharkNet3/Sugoi-32B-Ultra-IQ3_M-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 DharkNet3/Sugoi-32B-Ultra-IQ3_M-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 DharkNet3/Sugoi-32B-Ultra-IQ3_M-GGUF:IQ3_M
# Run inference directly in the terminal:
llama cli -hf DharkNet3/Sugoi-32B-Ultra-IQ3_M-GGUF:IQ3_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf DharkNet3/Sugoi-32B-Ultra-IQ3_M-GGUF:IQ3_M
# Run inference directly in the terminal:
llama cli -hf DharkNet3/Sugoi-32B-Ultra-IQ3_M-GGUF:IQ3_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 DharkNet3/Sugoi-32B-Ultra-IQ3_M-GGUF:IQ3_M
# Run inference directly in the terminal:
./llama-cli -hf DharkNet3/Sugoi-32B-Ultra-IQ3_M-GGUF:IQ3_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 DharkNet3/Sugoi-32B-Ultra-IQ3_M-GGUF:IQ3_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf DharkNet3/Sugoi-32B-Ultra-IQ3_M-GGUF:IQ3_M

Use Docker

docker model run hf.co/DharkNet3/Sugoi-32B-Ultra-IQ3_M-GGUF:IQ3_M

LM Studio
Jan
Ollama
How to use DharkNet3/Sugoi-32B-Ultra-IQ3_M-GGUF with Ollama:
```
ollama run hf.co/DharkNet3/Sugoi-32B-Ultra-IQ3_M-GGUF:IQ3_M
```
Unsloth Desktop

How to use DharkNet3/Sugoi-32B-Ultra-IQ3_M-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf DharkNet3/Sugoi-32B-Ultra-IQ3_M-GGUF:IQ3_M

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": "DharkNet3/Sugoi-32B-Ultra-IQ3_M-GGUF:IQ3_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use DharkNet3/Sugoi-32B-Ultra-IQ3_M-GGUF with Docker Model Runner:
```
docker model run hf.co/DharkNet3/Sugoi-32B-Ultra-IQ3_M-GGUF:IQ3_M
```

Lemonade

How to use DharkNet3/Sugoi-32B-Ultra-IQ3_M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull DharkNet3/Sugoi-32B-Ultra-IQ3_M-GGUF:IQ3_M

Run and chat with the model

lemonade run user.Sugoi-32B-Ultra-IQ3_M-GGUF-IQ3_M

List all available models

lemonade list

Hermes Agent

How to use DharkNet3/Sugoi-32B-Ultra-IQ3_M-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 DharkNet3/Sugoi-32B-Ultra-IQ3_M-GGUF:IQ3_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 DharkNet3/Sugoi-32B-Ultra-IQ3_M-GGUF:IQ3_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use DharkNet3/Sugoi-32B-Ultra-IQ3_M-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf DharkNet3/Sugoi-32B-Ultra-IQ3_M-GGUF:IQ3_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 "DharkNet3/Sugoi-32B-Ultra-IQ3_M-GGUF:IQ3_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"

Sugoi-32B-Ultra-GGUF (IQ3_M)

Overview

This is an IQ3_M quantized GGUF version of the Sugoi-32B-Ultra translation model.

This specific quantization was calibrated using a custom Importance Matrix (imatrix) generated from a high-quality Japanese-to-English translation dataset.

It has been strictly optimized with a targeted chunk size (-c 2048) to perfectly preserve the attention weights required for a 100-line rolling conversational buffer.

This makes it exceptionally stable for translating continuous media (Visual Novels, Light Novels, and Subtitles) where maintaining character voice, tone, and pronoun consistency over long scenes is critical.

Hardware Requirements

VRAM: ~14.5 GB peak usage. Fits comfortably on 16GB GPUs (e.g., RTX 4080, RX 7800 XT).
RAM: 16GB+ System RAM recommended for context offloading.
Context Window: 4096 (Up to 150 lines of history) or 8192 (Up to 300 lines).

Usage

If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files.

Downloads last month: 34

GGUF

Model size

33B params

Architecture

qwen2

Hardware compatibility

3-bit

Model tree for DharkNet3/Sugoi-32B-Ultra-IQ3_M-GGUF

Base model

Qwen/Qwen2.5-32B

Finetuned

Qwen/Qwen2.5-32B-Instruct

Quantized

sugoitoolkit/Sugoi-32B-Ultra-GGUF

Quantized

(1)

this model

DharkNet3
/

Sugoi-32B-Ultra-IQ3_M-GGUF

Sugoi-32B-Ultra-GGUF (IQ3_M)

Overview

Hardware Requirements

Usage

Model tree for DharkNet3/Sugoi-32B-Ultra-IQ3_M-GGUF

Datasets used to train DharkNet3/Sugoi-32B-Ultra-IQ3_M-GGUF