Instructions to use jedisct1/MiMo-V2.5-coder-Q2-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use jedisct1/MiMo-V2.5-coder-Q2-v2 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 jedisct1/MiMo-V2.5-coder-Q2-v2
# Run inference directly in the terminal:
llama cli -hf jedisct1/MiMo-V2.5-coder-Q2-v2

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf jedisct1/MiMo-V2.5-coder-Q2-v2
# Run inference directly in the terminal:
llama cli -hf jedisct1/MiMo-V2.5-coder-Q2-v2

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf jedisct1/MiMo-V2.5-coder-Q2-v2
# Run inference directly in the terminal:
./build/bin/llama cli -hf jedisct1/MiMo-V2.5-coder-Q2-v2

Use Docker

docker model run hf.co/jedisct1/MiMo-V2.5-coder-Q2-v2

Llama new
LM Studio
Jan

vLLM

How to use jedisct1/MiMo-V2.5-coder-Q2-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jedisct1/MiMo-V2.5-coder-Q2-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jedisct1/MiMo-V2.5-coder-Q2-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jedisct1/MiMo-V2.5-coder-Q2-v2

Ollama
How to use jedisct1/MiMo-V2.5-coder-Q2-v2 with Ollama:
```
ollama run hf.co/jedisct1/MiMo-V2.5-coder-Q2-v2
```
Unsloth Desktop

How to use jedisct1/MiMo-V2.5-coder-Q2-v2 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jedisct1/MiMo-V2.5-coder-Q2-v2

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": "jedisct1/MiMo-V2.5-coder-Q2-v2"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use jedisct1/MiMo-V2.5-coder-Q2-v2 with Docker Model Runner:
```
docker model run hf.co/jedisct1/MiMo-V2.5-coder-Q2-v2
```

Lemonade

How to use jedisct1/MiMo-V2.5-coder-Q2-v2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull jedisct1/MiMo-V2.5-coder-Q2-v2

Run and chat with the model

lemonade run user.MiMo-V2.5-coder-Q2-v2-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use jedisct1/MiMo-V2.5-coder-Q2-v2 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jedisct1/MiMo-V2.5-coder-Q2-v2

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 jedisct1/MiMo-V2.5-coder-Q2-v2

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use jedisct1/MiMo-V2.5-coder-Q2-v2 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jedisct1/MiMo-V2.5-coder-Q2-v2

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 "jedisct1/MiMo-V2.5-coder-Q2-v2" \
  --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"

MiMo-V2.5-coder-Q2-v2

File size: 1,553 Bytes

84ae63d

#!/usr/bin/env bash
set -euo pipefail

SCRIPT_DIR=$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)
LLAMA_SERVER=${LLAMA_SERVER:-llama-server}

if ! command -v "$LLAMA_SERVER" >/dev/null 2>&1; then
  echo "llama-server was not found. Install llama.cpp or set LLAMA_SERVER=/path/to/llama-server." >&2
  exit 1
fi

if [[ -n "${MIMO_MODEL:-}" ]]; then
  MODEL=$MIMO_MODEL
else
  shopt -s nullglob
  CANDIDATES=("$SCRIPT_DIR"/MiMo-V2.5-coder-Q2-00001-of-*.gguf)
  shopt -u nullglob

  if [[ ${#CANDIDATES[@]} -eq 0 ]]; then
    echo "No first GGUF shard found next to run-server.sh." >&2
    exit 1
  fi

  MODEL=${CANDIDATES[0]}
fi

ARGS=(
  --model "$MODEL"
  --host "${MIMO_HOST:-127.0.0.1}"
  --port "${MIMO_PORT:-8080}"
  --ctx-size "${MIMO_CTX:-100000}"
  --parallel "${MIMO_PARALLEL:-1}"
  --batch-size "${MIMO_BATCH:-512}"
  --ubatch-size "${MIMO_UBATCH:-128}"
  --threads "${MIMO_THREADS:-12}"
  --threads-batch "${MIMO_THREADS_BATCH:-18}"
  --prio "${MIMO_PRIO:-0}"
  --poll "${MIMO_POLL:-80}"
  --flash-attn on
  --jinja
  --fit "${MIMO_FIT:-on}"
  --fit-target "${MIMO_FIT_TARGET:-4096}"
  --fit-ctx "${MIMO_FIT_CTX:-100000}"
  --gpu-layers "${MIMO_GPU_LAYERS:-auto}"
  --cache-type-k "${MIMO_CACHE_K:-f16}"
  --cache-type-v "${MIMO_CACHE_V:-f16}"
  --reasoning "${MIMO_REASONING:-off}"
)

if [[ "${MIMO_CPU_MOE:-0}" == "1" ]]; then
  ARGS+=(--cpu-moe)
fi

if [[ -n "${MIMO_DEVICE:-}" ]]; then
  ARGS+=(--device "$MIMO_DEVICE")
fi

if [[ -n "${MIMO_TOOLS:-}" ]]; then
  ARGS+=(--tools "$MIMO_TOOLS")
fi

exec "$LLAMA_SERVER" "${ARGS[@]}" "$@"