Instructions to use orcarouter/MiniMax-M3.1-Flash-abliterated-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 orcarouter/MiniMax-M3.1-Flash-abliterated-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 orcarouter/MiniMax-M3.1-Flash-abliterated-GGUF
# Run inference directly in the terminal:
llama cli -hf orcarouter/MiniMax-M3.1-Flash-abliterated-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf orcarouter/MiniMax-M3.1-Flash-abliterated-GGUF
# Run inference directly in the terminal:
llama cli -hf orcarouter/MiniMax-M3.1-Flash-abliterated-GGUF

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 orcarouter/MiniMax-M3.1-Flash-abliterated-GGUF
# Run inference directly in the terminal:
./build/bin/llama cli -hf orcarouter/MiniMax-M3.1-Flash-abliterated-GGUF

Use Docker

docker model run hf.co/orcarouter/MiniMax-M3.1-Flash-abliterated-GGUF

Llama new
LM Studio
Jan

vLLM

How to use orcarouter/MiniMax-M3.1-Flash-abliterated-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "orcarouter/MiniMax-M3.1-Flash-abliterated-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "orcarouter/MiniMax-M3.1-Flash-abliterated-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/orcarouter/MiniMax-M3.1-Flash-abliterated-GGUF

Ollama
How to use orcarouter/MiniMax-M3.1-Flash-abliterated-GGUF with Ollama:
```
ollama run hf.co/orcarouter/MiniMax-M3.1-Flash-abliterated-GGUF
```
Unsloth Desktop

How to use orcarouter/MiniMax-M3.1-Flash-abliterated-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf orcarouter/MiniMax-M3.1-Flash-abliterated-GGUF

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": "orcarouter/MiniMax-M3.1-Flash-abliterated-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use orcarouter/MiniMax-M3.1-Flash-abliterated-GGUF with Docker Model Runner:
```
docker model run hf.co/orcarouter/MiniMax-M3.1-Flash-abliterated-GGUF
```

Lemonade

How to use orcarouter/MiniMax-M3.1-Flash-abliterated-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull orcarouter/MiniMax-M3.1-Flash-abliterated-GGUF

Run and chat with the model

lemonade run user.MiniMax-M3.1-Flash-abliterated-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use orcarouter/MiniMax-M3.1-Flash-abliterated-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 orcarouter/MiniMax-M3.1-Flash-abliterated-GGUF

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 orcarouter/MiniMax-M3.1-Flash-abliterated-GGUF

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use orcarouter/MiniMax-M3.1-Flash-abliterated-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf orcarouter/MiniMax-M3.1-Flash-abliterated-GGUF

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 "orcarouter/MiniMax-M3.1-Flash-abliterated-GGUF" \
  --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"

You need to agree to share your Hugging Face information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

MiniMax-M3.1-Flash-abliterated GGUF

🛡️ New from Orca — OrcaCyber Zero 1.5

Post-trained for cybersecurity: vulnerability analysis, vulnerability reproduction, red teaming & offensive-security research. 98.01% pass@1 on CyberGym Level 1 · 1M context · function calling · OpenAI-compatible API.

🛡️ New from Orca — OrcaCyber MiniMax-M3.1-Flash

No 128 GB box? Run MiniMax-M3.1-Flash Abliterated as a hosted, OpenAI-compatible API on OrcaRouter: no download, no GPUs, one API key.

🔌 New from Orca — Orca Connect

Running this GGUF in llama.cpp? Orca Connect puts the rig under your desk behind your usual OrcaRouter API key, next to 200+ hosted models, reachable from a laptop, a phone or a cloud agent. Outbound only: no port forwarding, no tunnel, no firewall rule. Requests your own hardware serves cost $0, and orca-connect claude points Claude Code at your rig for one session.

The 426B uncensored MiniMax-M3.1-Flash, in 128 GB of RAM.

112 GB in memory · fits a 128 GB machine · llama.cpp

OrcaRouter AI Gateway · X · Discord · GitHub · All Models

The full MiniMax-M3.1-Flash, run locally.

These are GGUF builds of the abliterated (refusal-removed) MiniMax-M3.1-Flash. It is a 426B-parameter MoE with 128 routed experts (top-4) and one shared expert. It uses MiniMax Sparse Attention on all 60 layers and has a 1M-token context.

Routed experts are 97% of the weights, so that is where the bits were spent. Each group of expert layers got its own precision from measured KL divergence, not from a hand-set rule.

The smallest public GGUF of this model so far is 129 GB, which needs a machine with more than 128 GB. Mix-128G is 112 GB and fits one.

⚠️ Disclaimer — read before use

This model is built on an abliterated base whose safety alignment has been substantially reduced. The refusal direction was orthogonalized out of every matrix that writes the residual stream. As a result, it will comply with many harmful, unethical, offensive, or illegal requests that the original MiniMax-M3.1-Flash would refuse.

It is released strictly for legitimate research: interpretability, AI-safety and refusal-mechanism study, red-teaming, and robustness evaluation.
You assume full responsibility for how you use it and for everything it generates. Add your own safety, moderation, and abuse-prevention layers before any deployment.
Use must comply with the MiniMax Community License inherited from the base model, including its prohibited-use appendix, and with all applicable law.
The authors accept no liability for misuse. Its outputs do not reflect the views of the uploaders or of MiniMax.

Pick a build

Build	In memory	Download	Experts	KLD ↓	Top-1 ↑	PPL vs. original
`Mix-128G`	111.9 GB	111.9 GB	1.98 bpw	1.061	67.0%	+34%

Mix-128G fits a 128 GB machine. That covers a 128 GB Mac, a 128 GB PC running on CPU, or GPUs with ~120 GB of VRAM in total. This model was quantization-aware trained at NVFP4 (4 bits), and going below 2 bits costs it a lot. On held-out text, two tokens in three still match the original's choice, and perplexity is a third higher.

Use Mix-128G to run the model on a 128 GB box. Do not expect it to match the full-precision model.

Evaluation

All builds are scored against the lossless GGUF of the same checkpoint. In that GGUF the experts stay native NVFP4, and MXFP8 is decoded bit-exact to BF16; it was verified element by element against the safetensors.

Scoring uses full-vocabulary KLD on held-out chat text: 32 windows of 4096 tokens across English prose, English chat, Chinese chat and Python code, all rendered through the model's chat template. M3.1 is a chat model and does not continue raw text well. The precision search never saw this text.

Every build is compared with two others at or near its size, quantized from the same weights with the same importance matrix:

llama.cpp's own mixture
unsloth's UD-IQ1_M recipe, the smallest build of unsloth's GGUFs of this model. We read its per-tensor types from their file and rebuilt it here.

	In memory	Fits 128 GB	KLD ↓	KLD p99	Top-1 ↑	PPL vs. original
Mix-128G (this repo)	111.9 GB	yes	1.061	10.73	66.96%	+34.0%
llama.cpp `IQ2_XXS`	112.3 GB	yes	2.466	13.84	50.78%	+77.3%
unsloth `UD-IQ1_M` recipe	129.4 GB	no	0.876	10.49	70.59%	+0.6%

At the same size, Mix-128G has less than half the KL divergence of llama.cpp's IQ2_XXS. unsloth's smallest recipe scores better, but it is 17.5 GB larger and needs more than 128 GB.

Method note. These are full-vocabulary KLD and next-token agreement on held-out text at 4k context, not a downstream benchmark. Even Q5_K (5.5 bpw) scores KLD ≈0.04 on this model, so the absolute numbers here are higher than on models without QAT.

Refusal and capability of the abliterated model

Measured on the unquantized abliterated checkpoint, not re-measured on these GGUF builds. The KLD above is how far each build sits from that checkpoint.

Setup.

Runtime: vLLM, TP4, fp8 KV cache.
Decoding: greedy, thinking disabled.
Scoring: refusal is judged by a rule-based opening-phrase classifier. Treat the numbers as indicative, not publication-grade.

Safety: harmful-prompt refusal (lower = more uncensored). Average 54.9%, against 94.4% for the base model.

Benchmark	n	Base	Abliterated	Δ
AdvBench	100	100%	44%	−56
JailbreakBench (harmful)	100	96%	55%	−41
StrongREJECT	100	98%	42%	−56
HarmBench (standard)	100	97%	63%	−34
MaliciousInstruct	100	95%	51%	−44
SimpleSafetyTests	100	88%	64%	−24
ForbiddenQuestions	100	99%	47%	−52

Over-refusal: benign prompts wrongly refused (lower = better).

Benchmark	n	Base	Abliterated
XSTest-safe	250	8.8%	2.4%

Capability retention.

Benchmark	n	Base	Abliterated
MMLU (0-shot)	300	84.0%	83.0%
MMLU-Pro (CoT)	250	60.4%	60.0%
GSM8K (CoT)	150	96.7%	97.3%

How the precision was chosen

The budget is set on the bytes that have to fit in memory.

Measure. For every group of tensors, the search measures the real KLD of moving it one precision level up and one level down. Groups are as follows:
- routed experts: one projection (gate, up or down) over two layers
- attention and shared experts: ten layers at a time
- leading dense FFN: one group for layers 0–2
- embedding and output head: one group each
Each measurement runs llama.cpp's own kernels.
Choose. A knapsack picks the combination of moves that fits the budget exactly.
Accept. Only steps whose candidate KLD was actually measured lower are kept.

The checkpoint ships each expert's NVFP4 global scale as a separate tensor. During quantization, that scale is folded into the expert's weights, so every GGUF here holds experts at their true magnitude.

Mix-128G puts its bits as follows:

Part	Type
Routed experts `gate`	IQ2_XXS
Routed experts `up`	IQ2_XXS (one layer pair IQ1_M)
Routed experts `down`	IQ1_M, with 7 of 29 layer pairs at IQ2_XXS
Attention, shared expert, dense FFN (layers 0–2)	Q5_K
Token embedding / output head	Q4_K / Q5_K
Router, norms, sparse-attention indexer	F32, as shipped

The importance matrix comes from 800k tokens of chat-formatted text:

English prose (wikitext-2)
English chat (ultrachat_200k)
Chinese chat (sharegpt_zh)
Python code (codeparrot)

This is the first release of Mix-128G, taken after one round of the search. Later rounds are running and will replace it here if they score better.

What's in this repo

Path	Size	Contents
`Mix-128G/…-00001-of-00003.gguf` … `00003`	111.9 GB	the 128 GB build
`imatrix.gguf`	0.9 GB	the importance matrix the builds were quantized with

The chat template is embedded in each build. The vision projector (mmproj) and the DSpark speculative drafter are not included yet.

Serving (llama.cpp)

MiniMax-M3.1 is not in llama.cpp master yet. Build the PR that adds it, ggml-org/llama.cpp#31192. These files were made and tested at commit 6b95a99:

git clone https://github.com/ggml-org/llama.cpp && cd llama.cpp
git fetch origin pull/31192/head:pr-31192 && git checkout 6b95a99
cmake -B build -DGGML_CUDA=ON && cmake --build build -j --target llama-server llama-cli
# Mac: cmake -B build (Metal is on by default) · CPU only: cmake -B build

hf download orcarouter/MiniMax-M3.1-Flash-abliterated-GGUF --include "Mix-128G/*" --local-dir ./m31-gguf

# One GPU with ~120 GB+ of VRAM (tested on 1 x H200)
llama-server -m m31-gguf/Mix-128G/MiniMax-M3.1-Flash-abliterated-Mix-128G-00001-of-00003.gguf \
  -ngl 99 -c 32768 --jinja

# CPU only or Apple Silicon, 128 GB RAM
llama-server -m m31-gguf/Mix-128G/MiniMax-M3.1-Flash-abliterated-Mix-128G-00001-of-00003.gguf \
  -ngl 0 -c 16384 --jinja      # on a Mac, use -ngl 99 to run on Metal

Memory. The KV cache costs about 135 KB per token: 16k of context adds ~2.2 GB on top of the weights, and 32k adds ~4.4 GB.
128 GB Mac. macOS lets the GPU wire only about 75% of RAM by default. Raise the limit before loading on Metal, for example sudo sysctl iogpu.wired_limit_mb=122000, and close other apps.
Thinking is on by default. The reasoning comes back in message.reasoning_content, and the answer in message.content.
Point llama.cpp at the 00001 part. It finds the other two.

Measured with short prompts, one request at a time:

Build	Hardware	Prompt	Generation
Mix-128G	1 x H200 (CUDA)	~220 tok/s	~81 tok/s

CPU and Apple Metal speeds have not been measured yet.

Model details


Base model	The abliterated build of `MiniMaxAI/MiniMax-M3.1-Flash`
Architecture	`minimax-m3` in llama.cpp. 60 layers, hidden 6144, GQA 64 q / 4 kv × 128, MiniMax Sparse Attention on every layer (blocks of 128, top-16), 3 leading dense layers, 128 routed experts top-4 + 1 shared expert
Weights in these files	426B: 413B routed experts, 13B attention / shared expert / dense / embeddings / head. 4 of 128 experts active per token
Quantization	Per-group mixed precision found by measured-KLD search. Experts are IQ1_M–IQ2_XXS. Attention, shared expert and dense FFN are Q5_K. Uses an importance matrix.
Context	1,048,576 tokens (inherited; evaluated at 4k) · Vocabulary 200,064
Runtime	llama.cpp with PR #31192; text in, text out

Bias, risks, and limitations

Safety guardrails are substantially reduced, inherited from the abliterated base; see the disclaimer. The refusal and capability numbers above come from the unquantized checkpoint. Mix-128G sits far enough from it (KLD 1.06) that its behaviour may differ.
Mix-128G is heavily degraded. This is the cost of 2-bit post-training quantization on a model trained for 4-bit, not a tuning issue.
Tested on CUDA only. CPU and Apple Metal have not been run with these files yet.
No vision projector or DSpark drafter yet. Long-context behaviour was not tested: all measurements are at 4k context or on short chats.
Inherits the biases and limitations of MiniMax-M3.1-Flash.
Requires a llama.cpp build with PR #31192. Stock llama.cpp, Ollama and LM Studio will not load these files until it is merged.

License

The MiniMax Community License, inherited from the base model MiniMaxAI/MiniMax-M3.1-Flash. It covers non-commercial use. Commercial use requires "Built with MiniMax M3.1-Flash" attribution and a notice to, or authorization from, MiniMax. See the license for the terms and its prohibited uses.

One Gateway. Every Model.

Route Smarter · Ship Safer · Spend Less

Website · Models · GitHub · Discord · X

Downloads last month: 321

GGUF

Model size

426B params

Architecture

minimax-m3

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for orcarouter/MiniMax-M3.1-Flash-abliterated-GGUF

Base model

MiniMaxAI/MiniMax-M3.1-Flash

Quantized

(35)

this model