Instructions to use Felladrin/gguf-Q2_K_S-Mixed-AutoRound-MiniMax-M2.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Felladrin/gguf-Q2_K_S-Mixed-AutoRound-MiniMax-M2.5 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Felladrin/gguf-Q2_K_S-Mixed-AutoRound-MiniMax-M2.5",
	filename="MiniMax-M2.5-256x4.9B-Q2_K_S.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Felladrin/gguf-Q2_K_S-Mixed-AutoRound-MiniMax-M2.5 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Felladrin/gguf-Q2_K_S-Mixed-AutoRound-MiniMax-M2.5:Q2_K_S
# Run inference directly in the terminal:
llama-cli -hf Felladrin/gguf-Q2_K_S-Mixed-AutoRound-MiniMax-M2.5:Q2_K_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Felladrin/gguf-Q2_K_S-Mixed-AutoRound-MiniMax-M2.5:Q2_K_S
# Run inference directly in the terminal:
llama-cli -hf Felladrin/gguf-Q2_K_S-Mixed-AutoRound-MiniMax-M2.5:Q2_K_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 Felladrin/gguf-Q2_K_S-Mixed-AutoRound-MiniMax-M2.5:Q2_K_S
# Run inference directly in the terminal:
./llama-cli -hf Felladrin/gguf-Q2_K_S-Mixed-AutoRound-MiniMax-M2.5:Q2_K_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 Felladrin/gguf-Q2_K_S-Mixed-AutoRound-MiniMax-M2.5:Q2_K_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Felladrin/gguf-Q2_K_S-Mixed-AutoRound-MiniMax-M2.5:Q2_K_S

Use Docker

docker model run hf.co/Felladrin/gguf-Q2_K_S-Mixed-AutoRound-MiniMax-M2.5:Q2_K_S

LM Studio
Jan
Ollama
How to use Felladrin/gguf-Q2_K_S-Mixed-AutoRound-MiniMax-M2.5 with Ollama:
```
ollama run hf.co/Felladrin/gguf-Q2_K_S-Mixed-AutoRound-MiniMax-M2.5:Q2_K_S
```

Unsloth Studio new

How to use Felladrin/gguf-Q2_K_S-Mixed-AutoRound-MiniMax-M2.5 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 Felladrin/gguf-Q2_K_S-Mixed-AutoRound-MiniMax-M2.5 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 Felladrin/gguf-Q2_K_S-Mixed-AutoRound-MiniMax-M2.5 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Felladrin/gguf-Q2_K_S-Mixed-AutoRound-MiniMax-M2.5 to start chatting

Pi new

How to use Felladrin/gguf-Q2_K_S-Mixed-AutoRound-MiniMax-M2.5 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Felladrin/gguf-Q2_K_S-Mixed-AutoRound-MiniMax-M2.5:Q2_K_S

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": "Felladrin/gguf-Q2_K_S-Mixed-AutoRound-MiniMax-M2.5:Q2_K_S"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Felladrin/gguf-Q2_K_S-Mixed-AutoRound-MiniMax-M2.5 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Felladrin/gguf-Q2_K_S-Mixed-AutoRound-MiniMax-M2.5:Q2_K_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 Felladrin/gguf-Q2_K_S-Mixed-AutoRound-MiniMax-M2.5:Q2_K_S

Run Hermes

hermes

Docker Model Runner
How to use Felladrin/gguf-Q2_K_S-Mixed-AutoRound-MiniMax-M2.5 with Docker Model Runner:
```
docker model run hf.co/Felladrin/gguf-Q2_K_S-Mixed-AutoRound-MiniMax-M2.5:Q2_K_S
```

Lemonade

How to use Felladrin/gguf-Q2_K_S-Mixed-AutoRound-MiniMax-M2.5 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Felladrin/gguf-Q2_K_S-Mixed-AutoRound-MiniMax-M2.5:Q2_K_S

Run and chat with the model

lemonade run user.gguf-Q2_K_S-Mixed-AutoRound-MiniMax-M2.5-Q2_K_S

List all available models

lemonade list

A Q2_K_S-Mixed GGUF version of MiniMaxAI/MiniMax-M2.5 generated with intel/auto-round, where the embedding layer and lm-head layer have 8-bit precision and the non-specialized layers have 4-bit precision.

Script for reproducing this model.

pip install transformers==4.56.0 torch==2.9.1 auto_round==0.9.4

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from auto_round import AutoRound

model_name = "MiniMaxAI/MiniMax-M2.5"

model = AutoModelForCausalLM.from_pretrained(model_name, device_map="cpu", trust_remote_code=True, dtype="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)
layer_config = {}
for n, m in model.named_modules():
    if n == "lm_head" or isinstance(m,torch.nn.Embedding):
        layer_config[n] = {"bits": 8}
    elif isinstance(m, torch.nn.Linear) and (not "expert" in n or "shared_experts" in n) and n != "lm_head":
        layer_config[n] = {"bits": 4}

autoround = AutoRound(model, tokenizer, iters=0, layer_config=layer_config, nsamples=512, disable_opt_rtn=False)

autoround.quantize_and_save("/models/tmp_autoround", format="gguf:q2_k_s")

Downloads last month: 53

GGUF

Model size

229B params

Architecture

minimax-m2

Hardware compatibility

2-bit

Inference Providers NEW

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

Model tree for Felladrin/gguf-Q2_K_S-Mixed-AutoRound-MiniMax-M2.5

Base model

MiniMaxAI/MiniMax-M2.5

Quantized

(68)

this model