Instructions to use KikoCis/minimax-m2-expert-prune-heal with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use KikoCis/minimax-m2-expert-prune-heal 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 KikoCis/minimax-m2-expert-prune-heal
# Run inference directly in the terminal:
llama cli -hf KikoCis/minimax-m2-expert-prune-heal

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf KikoCis/minimax-m2-expert-prune-heal
# Run inference directly in the terminal:
llama cli -hf KikoCis/minimax-m2-expert-prune-heal

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 KikoCis/minimax-m2-expert-prune-heal
# Run inference directly in the terminal:
./llama-cli -hf KikoCis/minimax-m2-expert-prune-heal

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 KikoCis/minimax-m2-expert-prune-heal
# Run inference directly in the terminal:
./build/bin/llama-cli -hf KikoCis/minimax-m2-expert-prune-heal

Use Docker

docker model run hf.co/KikoCis/minimax-m2-expert-prune-heal

LM Studio
Jan
Ollama
How to use KikoCis/minimax-m2-expert-prune-heal with Ollama:
```
ollama run hf.co/KikoCis/minimax-m2-expert-prune-heal
```
Unsloth Desktop

How to use KikoCis/minimax-m2-expert-prune-heal with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf KikoCis/minimax-m2-expert-prune-heal

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": "KikoCis/minimax-m2-expert-prune-heal"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use KikoCis/minimax-m2-expert-prune-heal with Docker Model Runner:
```
docker model run hf.co/KikoCis/minimax-m2-expert-prune-heal
```

Lemonade

How to use KikoCis/minimax-m2-expert-prune-heal with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull KikoCis/minimax-m2-expert-prune-heal

Run and chat with the model

lemonade run user.minimax-m2-expert-prune-heal-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use KikoCis/minimax-m2-expert-prune-heal with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf KikoCis/minimax-m2-expert-prune-heal

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 KikoCis/minimax-m2-expert-prune-heal

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use KikoCis/minimax-m2-expert-prune-heal with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf KikoCis/minimax-m2-expert-prune-heal

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 "KikoCis/minimax-m2-expert-prune-heal" \
  --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"

MiniMax-M2 — Expert-Pruned (keep-192/256), GGUF

A research artifact on structurally compressing a 230B Mixture-of-Experts coding agent (MiniMax-M2: 256 experts/layer, top-8) by pruning experts — keeping it a working agent in a real tool-using loop, not just a fluent generator. This is the keep-192 point: 192 of 256 experts kept (top-K by measured code/agentic activation), ~30% smaller, still solves real SWE tasks.

👉 Full field report: ARTICLE.md.

The headline: capability scales smoothly with the expert budget

Evaluated as a real coding agent (a harness driving the model through a Dockerized repo: read, edit, run tests) on a 6-instance SWE-bench Verified probe set (the exact instances the un-pruned model resolves 6/6), served via Ollama:

Variant	Size (GGUF)	Experts kept	SWE resolved
Full M2 (IQ2_M)	78 GB	256 / 256	6 / 6
keep-192 (this repo)	~55 GB	192 / 256	3 / 6
keep-160	46 GB	160 / 256	1 / 6
IQ1 (all experts, 1.8-bit)	48 GB	256 / 256	0 / 6

Two findings worth taking away:

No cliff — agentic capability degrades smoothly as you remove experts (6 → 3 → 1), it doesn't collapse. You can drop a quarter of the experts and keep half the solving.
At a fixed size, prune > uniform-extreme-quant — keep-160 (46 GB, 160 experts at ~2.7-bit) resolves where IQ1 (48 GB, all 256 at 1.8-bit) resolves nothing. Concentrating the bit budget on fewer experts beats spreading it thin.

These models are untrained (pure pruned quant, no fine-tune) — so the resolves are genuine compressed-M2 capability, not memorization.

Use it

# Ollama (the GGUF is in this repo):
ollama create m2-pruned192 -f Modelfile
ollama run m2-pruned192

Or point any llama.cpp/GGUF runtime at M2-pruned192-IQ2.gguf. Use a generous context for agent loops (the M2 chat template + stop tokens are baked into the Modelfile).

Reproduce

# Prune the kept experts out of an IQ2_M GGUF of MiniMax-M2 (clean slice, no re-quant):
python prune_gguf_experts.py \
  --in MiniMax-M2-IQ2_M.gguf --out M2-pruned192.gguf \
  --keep 192 --strategy file --keep-file keep192_experts.json

keep192_experts.json is the per-layer expert keep-set (top-K by measured activation on a code/agentic calibration corpus).

Limitations

Research artifact, not a production release. At ~55 GB it solves 3/6 of this probe set; the full 78 GB quant solves 6/6 — pruning trades size for capability along the curve above.
Untrained. A recovery fine-tune ("heal") on top should push it further up the curve (separate work).
Honest framing: this is not "better than the full model" — it's a smaller point on a clean size↔capability curve, and at a fixed budget it beats a same-size uniform low-bit quant.

License

Apache-2.0, inheriting MiniMax-M2's terms. This repo adds a pruning recipe + a pruned GGUF derived from a quantized MiniMax-M2.

Downloads last month: 17

GGUF

Model size

173B params

Architecture

minimax-m2

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

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

Model tree for KikoCis/minimax-m2-expert-prune-heal

Base model

MiniMaxAI/MiniMax-M2

Quantized

(43)

this model