Instructions to use AesSedai/MiMo-V2.6-Flash-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-Flash-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-Flash-RL-GGUF:IQ2_S
# Run inference directly in the terminal:
llama cli -hf AesSedai/MiMo-V2.6-Flash-RL-GGUF:IQ2_S

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-Flash-RL-GGUF:IQ2_S
# Run inference directly in the terminal:
llama cli -hf AesSedai/MiMo-V2.6-Flash-RL-GGUF:IQ2_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 AesSedai/MiMo-V2.6-Flash-RL-GGUF:IQ2_S
# Run inference directly in the terminal:
./llama-cli -hf AesSedai/MiMo-V2.6-Flash-RL-GGUF:IQ2_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 AesSedai/MiMo-V2.6-Flash-RL-GGUF:IQ2_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AesSedai/MiMo-V2.6-Flash-RL-GGUF:IQ2_S

Use Docker

docker model run hf.co/AesSedai/MiMo-V2.6-Flash-RL-GGUF:IQ2_S

LM Studio
Jan
Ollama
How to use AesSedai/MiMo-V2.6-Flash-RL-GGUF with Ollama:
```
ollama run hf.co/AesSedai/MiMo-V2.6-Flash-RL-GGUF:IQ2_S
```
Unsloth Desktop

How to use AesSedai/MiMo-V2.6-Flash-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-Flash-RL-GGUF:IQ2_S

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-Flash-RL-GGUF:IQ2_S"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use AesSedai/MiMo-V2.6-Flash-RL-GGUF with Docker Model Runner:
```
docker model run hf.co/AesSedai/MiMo-V2.6-Flash-RL-GGUF:IQ2_S
```

Lemonade

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

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AesSedai/MiMo-V2.6-Flash-RL-GGUF:IQ2_S

Run and chat with the model

lemonade run user.MiMo-V2.6-Flash-RL-GGUF-IQ2_S

List all available models

lemonade list

Hermes Agent

How to use AesSedai/MiMo-V2.6-Flash-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-Flash-RL-GGUF:IQ2_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 AesSedai/MiMo-V2.6-Flash-RL-GGUF:IQ2_S

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use AesSedai/MiMo-V2.6-Flash-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-Flash-RL-GGUF:IQ2_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 "AesSedai/MiMo-V2.6-Flash-RL-GGUF:IQ2_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"

Updates

09/22/26: Added 3.5, 2.5, and 2.0 BPW quants using ed's bpw-size PR. The FFNs are the primarily quantized feature, rest of the model remains in Q8_0 / Q6_K

This repo contains specialized MoE-quants for XiaomiMiMo/MiMo-V2.6-Flash-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.

Quant	Size	Mixture	PPL	1-(Mean PPL(Q)/PPL(base))	KLD
MXFP4	162.89 GiB (4.52 BPW)	BF16 / MXFP4	5.149210 ± 0.030596	+0.0715%	-0.000000 ± 0.000000
Q3_K	137.75 GiB (3.82 BPW)	Q8_0 / Q3_K / Q3_K / MXFP4	5.177623 ± 0.030900	+0.6237%	0.123607 ± 0.000648
BPW3.5	126.19 GiB (3.50 BPW)	Q8_0 / varies	5.232510 ± 0.031063	+1.6904%	0.138808 ± 0.000718
IQ2_S	106.31 GiB (2.95 BPW)	Q6_K / IQ2_S / IQ2_S / Q3_K	5.404774 ± 0.032158	+5.0382%	0.178092 ± 0.000878
BPW2.5	90.14 GiB (2.50 BPW)	Q8_0 / varies	5.739578 ± 0.034587	+11.5449%	0.243713 ± 0.001158
BPW2.0	66.99 GiB (1.86 BPW)	Q6_K / varies	7.290888 ± 0.046722	+41.6936%	0.477636 ± 0.002111