For an instant local deployment, running a pre-configured shell script is ideal.
Follow the step-by-step instructions below.
All large files and heavy weights are downloaded automatically by the script.
The initial setup handles the heavy lifting, fine-tuning the environment for your device.
MiniMax-M2.7-NVFP4 is a highly optimized, 4-bit quantized variant of MiniMaxAI’s flagship 230-billion parameter sparse Mixture-of-Experts (MoE) foundation model, compressed via NVIDIA Model Optimizer using the cutting-edge NVFP4 (Nvidia Floating Point 4-bit) format. The architecture leverages a blockwise FP8 scaling scheme per 16 elements, dropping the previous Lightning Attention layers in favor of pure, hardware-optimized Grouped-Query Attention (GQA) with 48 query heads and 8 KV heads. This aggressive mathematical alignment allows the massive model to execute on a mere 10B active parameters per token, reducing VRAM demands dramatically down to 70 GB per GPU in Tensor Parallel setups. Tailored for self-evolving agent loops, multi-file code refactoring, and real-world system debugging, it delivers extreme processing throughput over an expansive 196,608-token context window while maintaining an exceptional 56.22% score on the SWE-Pro engineering benchmark.
| Specification | Detail |
|---|---|
| Total / Active Parameters | 230 Billion Total / 10 Billion Active per Token (Sparse MoE) |
| Quantization Layout | NVFP4 (4-bit Weights with Blockwise FP8 Scales via Nvidia Model Optimizer) |
| Context Window | 196,608 tokens (196k natively) |
| Hardware Baseline | Dual NVIDIA RTX PRO 6000 Blackwell (96GB GDDR7) or H100 Tensor Parallel |
| Attention Mechanism | Standard GQA Softmax (48 Query / 8 KV Heads) |
| Primary Execution Engines | vLLM Native Server, SGLang Backend with b12x |
| Core Benchmarks | SWE-Pro: 56.22% / Terminal Bench 2: 57.0% / VIBE-Pro: 55.6% |
https://candanchuesquiclub.es/category/zero-shot/
Share your thoughts
No Thoughts About How to Install MiniMax-M2.7-NVFP4 Windows 11 Direct EXE Setup