Instructions to use anikifoss/MiniMax-M2-HQ4_K with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use anikifoss/MiniMax-M2-HQ4_K with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="anikifoss/MiniMax-M2-HQ4_K",
	filename="MiniMax-M2-HQ4_K-00001-of-00004.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use anikifoss/MiniMax-M2-HQ4_K with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf anikifoss/MiniMax-M2-HQ4_K
# Run inference directly in the terminal:
llama-cli -hf anikifoss/MiniMax-M2-HQ4_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf anikifoss/MiniMax-M2-HQ4_K
# Run inference directly in the terminal:
llama-cli -hf anikifoss/MiniMax-M2-HQ4_K

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 anikifoss/MiniMax-M2-HQ4_K
# Run inference directly in the terminal:
./llama-cli -hf anikifoss/MiniMax-M2-HQ4_K

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 anikifoss/MiniMax-M2-HQ4_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf anikifoss/MiniMax-M2-HQ4_K

Use Docker

docker model run hf.co/anikifoss/MiniMax-M2-HQ4_K

LM Studio
Jan

vLLM

How to use anikifoss/MiniMax-M2-HQ4_K with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "anikifoss/MiniMax-M2-HQ4_K"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "anikifoss/MiniMax-M2-HQ4_K",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/anikifoss/MiniMax-M2-HQ4_K

Ollama
How to use anikifoss/MiniMax-M2-HQ4_K with Ollama:
```
ollama run hf.co/anikifoss/MiniMax-M2-HQ4_K
```

Unsloth Studio new

How to use anikifoss/MiniMax-M2-HQ4_K 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 anikifoss/MiniMax-M2-HQ4_K 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 anikifoss/MiniMax-M2-HQ4_K to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for anikifoss/MiniMax-M2-HQ4_K to start chatting

Pi new

How to use anikifoss/MiniMax-M2-HQ4_K with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf anikifoss/MiniMax-M2-HQ4_K

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": "anikifoss/MiniMax-M2-HQ4_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use anikifoss/MiniMax-M2-HQ4_K with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf anikifoss/MiniMax-M2-HQ4_K

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 anikifoss/MiniMax-M2-HQ4_K

Run Hermes

hermes

Docker Model Runner
How to use anikifoss/MiniMax-M2-HQ4_K with Docker Model Runner:
```
docker model run hf.co/anikifoss/MiniMax-M2-HQ4_K
```

Lemonade

How to use anikifoss/MiniMax-M2-HQ4_K with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull anikifoss/MiniMax-M2-HQ4_K

Run and chat with the model

lemonade run user.MiniMax-M2-HQ4_K-{{QUANT_TAG}}

List all available models

lemonade list

Model Card

High quality quantization of MiniMax-M2 without using imatrix.

Run

Currently llama.cpp does not return <think> token for this model. If you know how to fix that, please share in the "Community" section!

As a workaround, to inject the token in OpenWebUI, you can use the inject_think_token_filter.txt. You can add filters via Admin Panel -> Functions -> Filter -> + button on the right

llama.cpp - CPU experts offload

./build/bin/llama-server \
    --alias anikifoss/MiniMax-M2-HQ4_K \
    --model ~/Env/models/anikifoss/MiniMax-M2-HQ4_K/MiniMax-M2-HQ4_K-00001-of-00004.gguf \
    --temp 1.0 --top-k 0 --top-p 1.0 --min-p 0.02 \
    --repeat-penalty 1.04 --repeat-last-n 256 \
    --ctx-size 95000 \
    -ctk q8_0 -ctv q8_0 \
    -fa on \
    -b 1024 -ub 1024 \
    -ngl 99 \
    --device CUDA0 \
    -ot "blk\.([0-9])\.attn_.*=CUDA0" \
    -ot "blk\.([1-6][0-9])\.attn_.*=CUDA0" \
    -ot "blk\.([0-4])\.ffn_.*_exps.*=CUDA0" \
    -ot "blk\.([5-9])\.ffn_.*_exps.*=CPU" \
    -ot "blk\.([1-6][0-9])\.ffn_.*_exps.*=CPU" \
    --jinja \
    --parallel 1 \
    --threads 32 \
    --host 127.0.0.1 \
    --port 8090

llama.cpp - MI50 experts offload

./build/bin/llama-server \
    --alias anikifoss/MiniMax-M2-HQ4_K \
    --model ~/Env/models/anikifoss/MiniMax-M2-HQ4_K/MiniMax-M2-HQ4_K-00001-of-00004.gguf \
    --temp 1.0 --top-k 0 --top-p 1.0 --min-p 0.02 \
    --repeat-penalty 1.04 --repeat-last-n 256 \
    --ctx-size 95000 \
    -ctk q8_0 -ctv q8_0 \
    -fa on \
    -b 1024 -ub 1024 \
    -ngl 99 \
    --device CUDA0,ROCm0,ROCm1,ROCm2,ROCm3 \
    --tensor-split 1,0,0,0,0 \
    -ot "blk\.([0-9])\.attn_.*=CUDA0" \
    -ot "blk\.([1-6][0-9])\.attn_.*=CUDA0" \
    -ot "blk\.([0-9])\.ffn_.*_exps.*=ROCm0" \
    -ot "blk\.(1[0-9])\.ffn_.*_exps.*=ROCm1" \
    -ot "blk\.(2[0-9])\.ffn_.*_exps.*=ROCm2" \
    -ot "blk\.(3[0-9])\.ffn_.*_exps.*=ROCm3" \
    -ot "blk\.(4[0-3])\.ffn_.*_exps.*=ROCm0" \
    -ot "blk\.(4[4-7])\.ffn_.*_exps.*=ROCm1" \
    -ot "blk\.(4[8-9])\.ffn_.*_exps.*=ROCm2" \
    -ot "blk\.(5[0-1])\.ffn_.*_exps.*=ROCm2" \
    -ot "blk\.(5[2-5])\.ffn_.*_exps.*=ROCm3" \
    -ot "blk\.(5[6-9])\.ffn_.*_exps.*=CUDA0" \
    -ot "blk\.(6[0-9])\.ffn_.*_exps.*=CUDA0" \
    --jinja \
    --parallel 1 \
    --threads 32 \
    --host 127.0.0.1 \
    --port 8090

Quantization Recipe

Quantized with llama.cpp. See Custom Quants section in this detailed guide for all the quantization steps.

TARGET_MODEL="MiniMax-M2-HQ4_K"
mkdir -p ~/Env/models/anikifoss/$TARGET_MODEL
./build/bin/llama-quantize \
    --output-tensor-type Q8_0 \
    --token-embedding-type Q8_0 \
    --tensor-type attn_q=Q8_0 \
    --tensor-type attn_k=Q8_0 \
    --tensor-type attn_v=Q8_0 \
    --tensor-type ffn_down_exps=Q6_K \
    --tensor-type ffn_gate_exps=Q4_K \
    --tensor-type ffn_up_exps=Q4_K \
    /mnt/data/Models/MiniMaxAI/MiniMax-M2-GGUF/MiniMax-M2-256x4.9B-BF16-00001-of-00010.gguf \
    ~/Env/models/anikifoss/$TARGET_MODEL/$TARGET_MODEL.gguf \
    Q8_0 \
    32

Downloads last month: 5

GGUF

Model size

229B params

Architecture

minimax-m2

Hardware compatibility

Model tree for anikifoss/MiniMax-M2-HQ4_K

Base model

MiniMaxAI/MiniMax-M2

Quantized

(47)

this model