Instructions to use AesSedai/MiMo-V2.6-Pro-RL-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 AesSedai/MiMo-V2.6-Pro-RL-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 AesSedai/MiMo-V2.6-Pro-RL-GGUF:MXFP4
# Run inference directly in the terminal:
llama cli -hf AesSedai/MiMo-V2.6-Pro-RL-GGUF:MXFP4

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf AesSedai/MiMo-V2.6-Pro-RL-GGUF:MXFP4
# Run inference directly in the terminal:
llama cli -hf AesSedai/MiMo-V2.6-Pro-RL-GGUF:MXFP4

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 AesSedai/MiMo-V2.6-Pro-RL-GGUF:MXFP4
# Run inference directly in the terminal:
./llama-cli -hf AesSedai/MiMo-V2.6-Pro-RL-GGUF:MXFP4

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 AesSedai/MiMo-V2.6-Pro-RL-GGUF:MXFP4
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AesSedai/MiMo-V2.6-Pro-RL-GGUF:MXFP4

Use Docker

docker model run hf.co/AesSedai/MiMo-V2.6-Pro-RL-GGUF:MXFP4

LM Studio
Jan
Ollama
How to use AesSedai/MiMo-V2.6-Pro-RL-GGUF with Ollama:
```
ollama run hf.co/AesSedai/MiMo-V2.6-Pro-RL-GGUF:MXFP4
```
Unsloth Desktop

How to use AesSedai/MiMo-V2.6-Pro-RL-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AesSedai/MiMo-V2.6-Pro-RL-GGUF:MXFP4

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": "AesSedai/MiMo-V2.6-Pro-RL-GGUF:MXFP4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use AesSedai/MiMo-V2.6-Pro-RL-GGUF with Docker Model Runner:
```
docker model run hf.co/AesSedai/MiMo-V2.6-Pro-RL-GGUF:MXFP4
```

Lemonade

How to use AesSedai/MiMo-V2.6-Pro-RL-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AesSedai/MiMo-V2.6-Pro-RL-GGUF:MXFP4

Run and chat with the model

lemonade run user.MiMo-V2.6-Pro-RL-GGUF-MXFP4

List all available models

lemonade list

Hermes Agent

How to use AesSedai/MiMo-V2.6-Pro-RL-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 AesSedai/MiMo-V2.6-Pro-RL-GGUF:MXFP4

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 AesSedai/MiMo-V2.6-Pro-RL-GGUF:MXFP4

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use AesSedai/MiMo-V2.6-Pro-RL-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AesSedai/MiMo-V2.6-Pro-RL-GGUF:MXFP4

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 "AesSedai/MiMo-V2.6-Pro-RL-GGUF:MXFP4" \
  --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"

This repo contains specialized MoE-quants for XiaomiMiMo/MiMo-V2.6-Pro-RL. The idea being that given the huge size of the FFN tensors compared to the rest of the tensors in the model, it should be possible to achieve a better quality while keeping the overall size of the entire model smaller compared to a similar naive quantization. To that end, the quantization type default is kept in high quality and the FFN UP + FFN GATE tensors are quanted down along with the FFN DOWN tensors.

The MXFP4 quant is the "full quality" version, as the model has MXFP4 experts.

The BPW quants have been created targeting specific sizes, using ed's bpw-size PR. I've included the imatrix-bpw.gguf and bpw-state.bin files needed to produce other quants using his PR.

Quant	Size	Mixture	PPL	1-(Mean PPL(Q)/PPL(base))	KLD
MXFP4	537.99 GiB (4.52 BPW)	BF16 / MXFP4	3.172064 ± 0.015439	+0.0376%	-0.000000 ± 0.000000
BPW3.5	416.88 GiB (3.50 BPW)	Q8_0 / varies	3.231880 ± 0.015640	+1.9240%	0.141151 ± 0.000823
BPW3.0	357.32 GiB (3.00 BPW)	Q8_0 / varies	3.383461 ± 0.016667	+6.7044%	0.183875 ± 0.001023
BPW2.5	297.78 GiB (2.50 BPW)	Q6_K / varies	3.682749 ± 0.018545	+16.1431%	0.255708 ± 0.001335
BPW2.0	219.58 GiB (1.84 BPW)	Q6_K / varies	5.113859 ± 0.027763	+61.2761%	0.542302 ± 0.002336

Downloads last month: 24

GGUF

Model size

1T params

Architecture

mimo2

Hardware compatibility

4-bit

View +6 variants

Inference Providers NEW

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

Model tree for AesSedai/MiMo-V2.6-Pro-RL-GGUF

Base model

XiaomiMiMo/MiMo-V2.6-Pro-RL

Quantized

(5)

this model