MiniMax-Music3 — GGUF (f16)

GGUF conversion of MiniMaxAI/MiniMax-Music3 for HOT-Step CPP, a fully local desktop app for AI music generation with a native C++/GGML engine. As far as we know this is the first GGUF conversion of this model.

These files are downloaded automatically by HOT-Step's Model Manager when the MiniMax-Music3 backend is selected. They are not usable with llama.cpp alone: mm3-lm-f16.gguf is structurally a Qwen3 GGUF, but music generation requires the full five-module pipeline (LM → RVQ depth decoder → condition encoder → flow-matching DiT → vocoder) implemented in HOT-Step's engine.

Files

File	Size	Contents
mm3-lm-f16.gguf	17.2 GB	Global LM (8.59B, Qwen3 arch, 200k vocab incl. 16,384 semantic audio codes) + full tokenizer
mm3-synth-f16.gguf	6.4 GB	RVQ depth decoder (0.6B) + condition encoder (25M) + flow DiT (2.4B) + vocoder (54M), namespaced depth. / cond. / dit. / voc.
LICENSE	—	MiniMax-Music3 Community License (governs the weights)

Output: 44.1 kHz 16-bit stereo, up to 5 minutes. VRAM: ~24 GB at f16 (quantized variants may follow).

Conversion provenance

Converted 2026-08-13 with HOT-Step's engine/tools/convert-mm3.py from the bf16/fp16 safetensors published by MiniMax (via the Comfy-Org repackage). Vocoder weight-norm folded at conversion; vocoder and DiT Fourier/RoPE bases pinned F32; all 911 tensors shape-validated. The HOT-Step implementation is parity-validated against the official diffusers reference (per-module correlation ≥ 0.9999 vs fp32; full-pipeline replay 0.9988).

License

The model weights are subject to the MiniMax-Music3 Community License (included here as LICENSE, per its notice-preservation requirement). Notable terms: prominent display of "MiniMax-Music3" in commercial products, separate authorization above US$20M annual revenue, acceptable-use policy, and clear disclosure of AI generation for publicly distributed outputs. The conversion adds no additional restrictions.