Instructions to use hell0ks/MiMo-V2.5-GGUF-ko with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use hell0ks/MiMo-V2.5-GGUF-ko 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 hell0ks/MiMo-V2.5-GGUF-ko:IQ3_S
# Run inference directly in the terminal:
llama cli -hf hell0ks/MiMo-V2.5-GGUF-ko:IQ3_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf hell0ks/MiMo-V2.5-GGUF-ko:IQ3_S
# Run inference directly in the terminal:
llama cli -hf hell0ks/MiMo-V2.5-GGUF-ko:IQ3_S

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 hell0ks/MiMo-V2.5-GGUF-ko:IQ3_S
# Run inference directly in the terminal:
./llama-cli -hf hell0ks/MiMo-V2.5-GGUF-ko:IQ3_S

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 hell0ks/MiMo-V2.5-GGUF-ko:IQ3_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf hell0ks/MiMo-V2.5-GGUF-ko:IQ3_S

Use Docker

docker model run hf.co/hell0ks/MiMo-V2.5-GGUF-ko:IQ3_S

LM Studio
Jan
Ollama
How to use hell0ks/MiMo-V2.5-GGUF-ko with Ollama:
```
ollama run hf.co/hell0ks/MiMo-V2.5-GGUF-ko:IQ3_S
```

Unsloth Studio

How to use hell0ks/MiMo-V2.5-GGUF-ko 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 hell0ks/MiMo-V2.5-GGUF-ko 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 hell0ks/MiMo-V2.5-GGUF-ko to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for hell0ks/MiMo-V2.5-GGUF-ko to start chatting

How to use hell0ks/MiMo-V2.5-GGUF-ko with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf hell0ks/MiMo-V2.5-GGUF-ko:IQ3_S

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": "hell0ks/MiMo-V2.5-GGUF-ko:IQ3_S"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use hell0ks/MiMo-V2.5-GGUF-ko with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf hell0ks/MiMo-V2.5-GGUF-ko:IQ3_S

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 hell0ks/MiMo-V2.5-GGUF-ko:IQ3_S

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use hell0ks/MiMo-V2.5-GGUF-ko with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf hell0ks/MiMo-V2.5-GGUF-ko:IQ3_S

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 "hell0ks/MiMo-V2.5-GGUF-ko:IQ3_S" \
  --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"

Docker Model Runner
How to use hell0ks/MiMo-V2.5-GGUF-ko with Docker Model Runner:
```
docker model run hf.co/hell0ks/MiMo-V2.5-GGUF-ko:IQ3_S
```

Lemonade

How to use hell0ks/MiMo-V2.5-GGUF-ko with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull hell0ks/MiMo-V2.5-GGUF-ko:IQ3_S

Run and chat with the model

lemonade run user.MiMo-V2.5-GGUF-ko-IQ3_S

List all available models

lemonade list

MiMo-V2.5-GGUF-ko

This is basically same as AesSedai/MiMo-V2.5-GGUF, but with Korean-focused imatrix dataset.

How it was made

Generate Korean-focused imatrix calibration dataset (Total 2048 samples, Chat template applied for messages)

Dataset	Language	Type	Topic	Comment
EleutherAI/the_pile_deduplicated	English	text	English corpus	15%, 16384
KORMo-Team/Cosmopedia-ko-synth	Korean	text	Korean corpus	35%, 8192
Korean chat generated with Gemma 4	Korean	messages	Korean chat	35%, 8192
SWE-bench/SWE-smith-trajectories	English	messages	Tool calling	15%, 8192

Create imatrix using llama-imatrix with --parse-special flag
Followed AesSedai's quantize method

export TYPE_FFN_UP_EXPS=IQ2_S
export TYPE_FFN_GATE_EXPS=IQ2_S
export TYPE_FFN_DOWN_EXPS=IQ3_S
export TYPE_DEFAULT=Q6_K

llama-quantize \
    --allow-requantize \
    --tensor-type ffn_up_exps=$TYPE_FFN_UP_EXPS \
    --tensor-type ffn_gate_exps=$TYPE_FFN_GATE_EXPS \
    --tensor-type ffn_down_exps=$TYPE_FFN_DOWN_EXPS \
    --imatrix $imatrix $gguf_path $TYPE_DEFAULT

Acknowledgement

Special thanks to AesSedai for implementing MiMo support for llama.cpp and quantize method.

Downloads last month: 42

GGUF

Model size

310B params

Architecture

mimo2

Hardware compatibility

3-bit

View +1 variant

Inference Providers NEW

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

Model tree for hell0ks/MiMo-V2.5-GGUF-ko

Base model

XiaomiMiMo/MiMo-V2.5

Quantized

(29)

this model

hell0ks
/

MiMo-V2.5-GGUF-ko

MiMo-V2.5-GGUF-ko

How it was made

Acknowledgement

Model tree for hell0ks/MiMo-V2.5-GGUF-ko

Datasets used to train hell0ks/MiMo-V2.5-GGUF-ko