Read our How to Run MiniMax M3 Guide! See Unsloth Dynamic 2.0 GGUFs for our quantization benchmarks. EXPERIMENTAL GGUF / support for MiniMax M3 Jun 12 Update: You can now run MiniMax M3 in Unsloth Studio. See our Guide . Example of MiniMax M3 (5 bit GGUF) running in Unsloth Studio: EXPERIMENTAL GGUF / support for MiniMax M3 in llama.cpp: 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: Then run a quant. The model is large (~428B params), so offload across GPUs with ngl 99 or keep the weights in CPU RAM: Note: MiniMax Sparse Attention is not supported yet, so inference falls back to dense attention. MiniMax M3 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, ex…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy