Instructions to use choppedgarlic/MiniMax-M3.1-Flash-abliterated-Q3-4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use choppedgarlic/MiniMax-M3.1-Flash-abliterated-Q3-4 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 choppedgarlic/MiniMax-M3.1-Flash-abliterated-Q3-4 # Run inference directly in the terminal: llama cli -hf choppedgarlic/MiniMax-M3.1-Flash-abliterated-Q3-4
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf choppedgarlic/MiniMax-M3.1-Flash-abliterated-Q3-4 # Run inference directly in the terminal: llama cli -hf choppedgarlic/MiniMax-M3.1-Flash-abliterated-Q3-4
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 choppedgarlic/MiniMax-M3.1-Flash-abliterated-Q3-4 # Run inference directly in the terminal: ./build/bin/llama cli -hf choppedgarlic/MiniMax-M3.1-Flash-abliterated-Q3-4
Use Docker
docker model run hf.co/choppedgarlic/MiniMax-M3.1-Flash-abliterated-Q3-4
- Llama new
- LM Studio
- Jan
- Ollama
How to use choppedgarlic/MiniMax-M3.1-Flash-abliterated-Q3-4 with Ollama:
ollama run hf.co/choppedgarlic/MiniMax-M3.1-Flash-abliterated-Q3-4
- Unsloth Desktop
- Pi
How to use choppedgarlic/MiniMax-M3.1-Flash-abliterated-Q3-4 with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf choppedgarlic/MiniMax-M3.1-Flash-abliterated-Q3-4
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:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "choppedgarlic/MiniMax-M3.1-Flash-abliterated-Q3-4" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use choppedgarlic/MiniMax-M3.1-Flash-abliterated-Q3-4 with Docker Model Runner:
docker model run hf.co/choppedgarlic/MiniMax-M3.1-Flash-abliterated-Q3-4
- Lemonade
How to use choppedgarlic/MiniMax-M3.1-Flash-abliterated-Q3-4 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull choppedgarlic/MiniMax-M3.1-Flash-abliterated-Q3-4
Run and chat with the model
lemonade run user.MiniMax-M3.1-Flash-abliterated-Q3-4-{{QUANT_TAG}}List all available models
lemonade list
- Hermes Agent
How to use choppedgarlic/MiniMax-M3.1-Flash-abliterated-Q3-4 with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf choppedgarlic/MiniMax-M3.1-Flash-abliterated-Q3-4
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://127.0.0.1:9931/v1 hermes config set model.default choppedgarlic/MiniMax-M3.1-Flash-abliterated-Q3-4
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use choppedgarlic/MiniMax-M3.1-Flash-abliterated-Q3-4 with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf choppedgarlic/MiniMax-M3.1-Flash-abliterated-Q3-4
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://127.0.0.1:9931/v1 \ --custom-model-id "choppedgarlic/MiniMax-M3.1-Flash-abliterated-Q3-4" \ --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-M3.1-Flash abliterated Q3-4
Public copy of a mixed GGUF made so the file can be pulled onto another machine. Q3-4 names the two big expert precisions: routed gate and up are Q3_K, and the down-experts are 4-bit NVFP4 except the abliterated ones, which stay Q6_K. The whole file is 4.31 bits per weight. The MiniMax Community License applies, including its non-commercial terms and prohibited-uses appendix.
Built with MiniMax M3.1-Flash. This is a requantization of operationrange/MiniMax-M3.1-Flash-abliterated-GGUF revision ef198a171043c687a768a4179917ab6547672583. No new abliteration was run. The edited tensors are the ones that repo already stored as Q8_0.
| File | Size |
|---|---|
MiniMax-M3.1-Flash-abliterated-fit256.gguf |
214.03 GiB |
Tensor mix, from that abliterated Q8 file:
blk.16βblk.42ffn_down_exps(the abliterated experts): Q6_K- other routed down-experts: original NVFP4, copied
- routed gate and up experts: Q3_K
- attention Q/K/output, shared expert, dense lead FFN: Q8_0
- attention V, embeddings, output head: BF16
- norms, router, indexer, and per-expert
.scaletensors: copied
The per-expert scale tensors are required. DwarfStar multiplies gate and up by that scale before SwiGLU, and down by that scale before the routed reduction. A runtime that skips the scales prints token soup. Homebrew llama.cpp 0.7.0 does that on this file.
hf download choppedgarlic/MiniMax-M3.1-Flash-abliterated-Q3-4 --local-dir ./minimax-q3-4
The model will comply with requests the original refuses.
Measured on a 256 GB M3 Ultra
Resident in DwarfStar, context 65536. The weights file in this repo is the one that was measured. It was not rebuilt for these numbers.
| tok/s | |
|---|---|
| Decode, no drafter | 18.95 |
| Decode, DFlash2, predictable integers, temperature 0 | 31 |
| Prefill, 7472 tokens | 74 |
| Thinking on, sampled | about 20 |
The 31 tok/s figure is the greedy integer bench, at 94.9% DFlash2 acceptance. A normal thinking reply stays near 20 tok/s, because sampled turns commit one token at a time. Keeping argmax drafts during temperature-1 thinking locked repetitions.
Write-up, including the quant recipe and the gibberish notes: jjakemaness/dwarfstar-minimax-m31. Engine branch: minimax-m31-m3ultra. Pull request: antirez/ds4#1320, stacked on #1287.
- Downloads last month
- 11,547
We're not able to determine the quantization variants.
Model tree for choppedgarlic/MiniMax-M3.1-Flash-abliterated-Q3-4
Base model
MiniMaxAI/MiniMax-M3.1-Flash