Instructions to use Sciguy429/MiMo-V2.5-IK-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Sciguy429/MiMo-V2.5-IK-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Sciguy429/MiMo-V2.5-IK-GGUF",
	filename="BF16_IK/MiMo-V2.5-BF16-IK-00001-of-00022.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Sciguy429/MiMo-V2.5-IK-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 Sciguy429/MiMo-V2.5-IK-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf Sciguy429/MiMo-V2.5-IK-GGUF:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Sciguy429/MiMo-V2.5-IK-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf Sciguy429/MiMo-V2.5-IK-GGUF:BF16

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 Sciguy429/MiMo-V2.5-IK-GGUF:BF16
# Run inference directly in the terminal:
./llama-cli -hf Sciguy429/MiMo-V2.5-IK-GGUF:BF16

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 Sciguy429/MiMo-V2.5-IK-GGUF:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Sciguy429/MiMo-V2.5-IK-GGUF:BF16

Use Docker

docker model run hf.co/Sciguy429/MiMo-V2.5-IK-GGUF:BF16

LM Studio
Jan
Ollama
How to use Sciguy429/MiMo-V2.5-IK-GGUF with Ollama:
```
ollama run hf.co/Sciguy429/MiMo-V2.5-IK-GGUF:BF16
```

Unsloth Studio

How to use Sciguy429/MiMo-V2.5-IK-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 Sciguy429/MiMo-V2.5-IK-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 Sciguy429/MiMo-V2.5-IK-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Sciguy429/MiMo-V2.5-IK-GGUF to start chatting

How to use Sciguy429/MiMo-V2.5-IK-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Sciguy429/MiMo-V2.5-IK-GGUF:BF16

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": "Sciguy429/MiMo-V2.5-IK-GGUF:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Sciguy429/MiMo-V2.5-IK-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 Sciguy429/MiMo-V2.5-IK-GGUF:BF16

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 Sciguy429/MiMo-V2.5-IK-GGUF:BF16

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use Sciguy429/MiMo-V2.5-IK-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Sciguy429/MiMo-V2.5-IK-GGUF:BF16

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 "Sciguy429/MiMo-V2.5-IK-GGUF:BF16" \
  --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 Sciguy429/MiMo-V2.5-IK-GGUF with Docker Model Runner:
```
docker model run hf.co/Sciguy429/MiMo-V2.5-IK-GGUF:BF16
```

Lemonade

How to use Sciguy429/MiMo-V2.5-IK-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Sciguy429/MiMo-V2.5-IK-GGUF:BF16

Run and chat with the model

lemonade run user.MiMo-V2.5-IK-GGUF-BF16

List all available models

lemonade list

WIP ik_llama quants for MiMo-V2.5

This is a set of not QKV merged quants for MiMo-V2.5, compatible with mainline ik_llama.cpp.

Context:

Mainline lama.cpp opted to go against the base MiMo-V2.5 files and fuse the model's Q, K and V tensors together in this PR. This poses no functional issues, but completely broke already existing support from ik_llama. Since this change every mainline quant has had these fused tensors, making it essentially impossible to run MiMo-V2.5 on ik_llama without doing everything yourself. Worst still, this makes existing imatrix files equally incompatible.

Currently this repo just has the base converted BF16 tensors, two generated imatrix sets (one with Ubergram's corpus and the other made form Bartowski's), and a BF16 logits file generated at 512 ctx and a batch size of 2048.

Downloads last month: 726

GGUF

Model size

309B params

Architecture

mimo2

Hardware compatibility

16-bit

Inference Providers NEW

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

Model tree for Sciguy429/MiMo-V2.5-IK-GGUF

Base model

XiaomiMiMo/MiMo-V2.5

Quantized

(29)

this model