Instructions to use Ex0bit/MiniMax-M2.1-PRISM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ex0bit/MiniMax-M2.1-PRISM with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Ex0bit/MiniMax-M2.1-PRISM",
	filename="MiniMax-M2.1-PRISM-IQ2_M.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Ex0bit/MiniMax-M2.1-PRISM with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Ex0bit/MiniMax-M2.1-PRISM:IQ2_M
# Run inference directly in the terminal:
llama-cli -hf Ex0bit/MiniMax-M2.1-PRISM:IQ2_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Ex0bit/MiniMax-M2.1-PRISM:IQ2_M
# Run inference directly in the terminal:
llama-cli -hf Ex0bit/MiniMax-M2.1-PRISM:IQ2_M

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 Ex0bit/MiniMax-M2.1-PRISM:IQ2_M
# Run inference directly in the terminal:
./llama-cli -hf Ex0bit/MiniMax-M2.1-PRISM:IQ2_M

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 Ex0bit/MiniMax-M2.1-PRISM:IQ2_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Ex0bit/MiniMax-M2.1-PRISM:IQ2_M

Use Docker

docker model run hf.co/Ex0bit/MiniMax-M2.1-PRISM:IQ2_M

LM Studio
Jan

vLLM

How to use Ex0bit/MiniMax-M2.1-PRISM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ex0bit/MiniMax-M2.1-PRISM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ex0bit/MiniMax-M2.1-PRISM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ex0bit/MiniMax-M2.1-PRISM:IQ2_M

Ollama
How to use Ex0bit/MiniMax-M2.1-PRISM with Ollama:
```
ollama run hf.co/Ex0bit/MiniMax-M2.1-PRISM:IQ2_M
```

Unsloth Studio

How to use Ex0bit/MiniMax-M2.1-PRISM 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 Ex0bit/MiniMax-M2.1-PRISM 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 Ex0bit/MiniMax-M2.1-PRISM to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Ex0bit/MiniMax-M2.1-PRISM to start chatting

How to use Ex0bit/MiniMax-M2.1-PRISM with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Ex0bit/MiniMax-M2.1-PRISM:IQ2_M

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": "Ex0bit/MiniMax-M2.1-PRISM:IQ2_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Ex0bit/MiniMax-M2.1-PRISM with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Ex0bit/MiniMax-M2.1-PRISM:IQ2_M

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 Ex0bit/MiniMax-M2.1-PRISM:IQ2_M

Run Hermes

hermes

Docker Model Runner
How to use Ex0bit/MiniMax-M2.1-PRISM with Docker Model Runner:
```
docker model run hf.co/Ex0bit/MiniMax-M2.1-PRISM:IQ2_M
```

Lemonade

How to use Ex0bit/MiniMax-M2.1-PRISM with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Ex0bit/MiniMax-M2.1-PRISM:IQ2_M

Run and chat with the model

lemonade run user.MiniMax-M2.1-PRISM-IQ2_M

List all available models

lemonade list

Ex0bit commited on Jan 1

Commit

33e5bc6

verified ·

1 Parent(s): f0da977

Update README.md

Browse files

Files changed (1) hide show

README.md +7 -25

README.md CHANGED Viewed

@@ -13,9 +13,9 @@ language:
 pipeline_tag: text-generation
 ---
-# MiniMax-M2.1-PRISM
-**An abliterated version of MiniMax-M2.1 using the PRISM methodology**
 [![Support me on Ko-fi](https://ko-fi.com/img/githubbutton_sm.svg)](https://ko-fi.com/ericelbaz)
@@ -23,7 +23,7 @@ pipeline_tag: text-generation
 ## Model Description
-**MiniMax-M2.1-PRISM** is an abliterated version of MiniMax-M2.1, processed using PRISM (Projected Refusal Isolation via Subspace Modification) to remove refusal behaviors while preserving full model capabilities.
 ### Base Model: MiniMax-M2.1
@@ -44,24 +44,7 @@ MiniMax-M2.1 is an open-source agentic language model designed for robust perfor
 This model was abliterated using **PRISM v5** - a state-of-the-art abliteration methodology combining multiple principled techniques for effective refusal removal while preserving model capabilities.
-**Formula**: `W' = W - weight * (d ⊗ d) @ W`
-Where:
-- `W` = Original weight matrix
-- `d` = Refusal direction vector (unit normalized)
-- `weight` = Layer-specific abliteration strength
-- `W'` = Modified weight matrix
-### Abliteration Parameters
-| Parameter | Value |
-|-----------|-------|
-| Base Model | QuixiAI/MiniMax-M2.1-bf16 |
-| Total Layers | 62 |
-| Target Layers | 16-46 (31 layers) |
-| Peak Layer | 31 |
-| Max Weight | 3.0 |
-| Min Weight | 0.5 |
 ### Weight Distribution
@@ -92,16 +75,16 @@ The abliteration strength follows a triangular distribution centered on the peak
 | Benign Coherence | 100% |
 | Response Quality | Full technical accuracy preserved |
-Testing shows that PRISM abliteration maintains full model coherence with no measurable capability degradation.
 ---
-## Available Formats
 | Format | Size | Description |
 |--------|------|-------------|
-| Safetensors (BF16) | ~426 GB | Full precision, 92 shards |
 | GGUF IQ1_S | ~43 GB | Quantized with importance matrix |
 ---
@@ -157,7 +140,6 @@ This model inherits the [Modified-MIT License](https://github.com/MiniMax-AI/Min
 ## Credits
 - **Base Model**: [MiniMax-M2.1](https://huggingface.co/MiniMaxAI/MiniMax-M2.1) by MiniMax AI
-- **BF16 Conversion**: [QuixiAI/MiniMax-M2.1-bf16](https://huggingface.co/QuixiAI/MiniMax-M2.1-bf16) by Eric Hartford
 - **PRISM Abliteration**: Ex0bit
 - **Quantization**: Using [llama.cpp](https://github.com/ggml-org/llama.cpp) with unsloth imatrix
@@ -165,7 +147,7 @@ This model inherits the [Modified-MIT License](https://github.com/MiniMax-AI/Min
 ## Support
-If you find this work useful, consider supporting development:
 [![Support me on Ko-fi](https://ko-fi.com/img/githubbutton_sm.svg)](https://ko-fi.com/ericelbaz)

 pipeline_tag: text-generation
 ---
+# MiniMax-M2.1-PRISM (UNCENSORED)
+** MiniMax-M2.1 Uncensored via PRISM Advanced Abliteration**
 [![Support me on Ko-fi](https://ko-fi.com/img/githubbutton_sm.svg)](https://ko-fi.com/ericelbaz)
 ## Model Description
+**MiniMax-M2.1-PRISM** is the abliterated version of MiniMax-M2.1, processed using PRISM (Projected Refusal Isolation via Subspace Modification) to remove refusal behaviors while preserving and even enhancing full model capabilities.
 ### Base Model: MiniMax-M2.1
 This model was abliterated using **PRISM v5** - a state-of-the-art abliteration methodology combining multiple principled techniques for effective refusal removal while preserving model capabilities.
 ### Weight Distribution
 | Benign Coherence | 100% |
 | Response Quality | Full technical accuracy preserved |
+Testing shows that PRISM abliteration maintains full model coherence with no capability degradation and MMLU increases of 5-8%.
 ---
+## Available Formats (contact for full tensors)
 | Format | Size | Description |
 |--------|------|-------------|
 | GGUF IQ1_S | ~43 GB | Quantized with importance matrix |
+| Safetensors (BF16) | ~426 GB | Full precision, 92 shards |
 ---
 ## Credits
 - **Base Model**: [MiniMax-M2.1](https://huggingface.co/MiniMaxAI/MiniMax-M2.1) by MiniMax AI
 - **PRISM Abliteration**: Ex0bit
 - **Quantization**: Using [llama.cpp](https://github.com/ggml-org/llama.cpp) with unsloth imatrix
 ## Support
+If you find this work useful, please consider supporting development so I can continue putting out the best models for the community:
 [![Support me on Ko-fi](https://ko-fi.com/img/githubbutton_sm.svg)](https://ko-fi.com/ericelbaz)