MiniMax M3 GGUF
MiniMax M3 GGUF by unsloth, a image-text-to-text model with multimodal capabilities. Understand and compare multimodal features, benchmarks, and capabilities.
Comparison
| Feature | MiniMax M3 GGUF | Interfaze |
|---|---|---|
| Input Modalities | text, image, video | image, text, audio, video, document |
| Native OCR | No | Yes |
| Long Document Processing | Yes | Yes |
| Language Support | 40 partial | 162+ |
| Native Speech-to-Text | No | Yes |
| Native Object Detection | No | Yes |
| Guardrail Controls | Yes | Yes |
| Context Input Size | 1M | 1M |
| Tool Calling | Yes | Tool calling supported + built in browser, code execution and web search |
Scaling
| Feature | MiniMax M3 GGUF | Interfaze |
|---|---|---|
| Scaling | Self-hosted/Provider-hosted with quantization | Unlimited |
View model card on Hugging Face
MiniMax-M3 support in llama.cpp is preliminary and not yet in a released build. To run these GGUFs, build llama.cpp from PR #24523:
git clone https://github.com/ggml-org/llama.cpp
cd llama.cpp
git fetch origin pull/24523/head:minimax-m3
git checkout minimax-m3
cmake -B build -DGGML_CUDA=ON
cmake --build build --config Release -j --target llama-cli llama-serverThen run a quant. The model is large (~428B params), so offload across GPUs with -ngl 99 or keep the weights in CPU RAM:
./build/bin/llama-cli -hf unsloth/MiniMax-M3-GGUF:UD-IQ1_MNote: MiniMax Sparse Attention is not supported yet, so inference falls back to dense attention.
Highlights:
- Native Multimodality: M3 undergoes mixed-modality training from the very first step, enabling deeper semantic fusion across text, image, and video.
- Context Scaling via Sparse Attention: M3 introduces MiniMax Sparse Attention (MSA) to improve long context efficiency. M3 delivers 9× prefill and 15× decode speedups compared to M2 at 1M context, reducing per-token compute to 1/20.
- Coding & Cowork Capability: M3 achieves frontier-level performance across long-horizon agentic benchmarks, excelling in both coding and cowork.
Model Details
| Architecture | MoE + MSA (MiniMax Sparse Attention) |
| Total Parameters | ~428B |
| Activated Parameters | ~23B |
| Experts | 128 (4 active per token) |
| Layers | 60 |
| Context Length | 1M tokens |
| Modalities | Text, Image, Video |
| Precision | bfloat16 |
| Transformers | ≥ 4.52.4 (trust_remote_code=True) |
| License | MiniMax Community License |
How to Use
M3 supports two reasoning modes:
- thinking — for complex reasoning, agentic tasks, and long-horizon collaboration.
- non-thinking — for latency-sensitive scenarios such as chat and code completion.
Local Deployment
Download the model:
hf download MiniMaxAI/MiniMax-M3 --local-dir MiniMax-M3You can also get model weights from ModelScope.
Inference Parameters
We recommend the following parameters for best performance: temperature=1.0, top_p=0.95, top_k=40. Default system prompt:
You are a helpful assistant. Your name is MiniMax-M3 and was built by MiniMax.