scragnog/MiniMax-Music3-GGUF

MiniMax-Music3 — GGUF

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-*.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.

Split format (one GGUF per component)

Since 2026-08-14 the repo carries one file per pipeline component, so each can be picked at its own quantisation and swapped without re-downloading the others:

File family	Component	Quants
mm3-lm-<quant>.gguf	Global LM (8.59B, Qwen3 arch, 200k vocab incl. 16,384 semantic audio codes) + full tokenizer	f16 · q8_0 · Q6_K · Q5_K_M/S · Q4_K_M/S · NVFP4 · MXFP4 · Q3_K_L/M/S · Q2_K
mm3-dit-<quant>.gguf	Flow-matching DiT (2.4B)	same ladder
mm3-depth-<quant>.gguf	RVQ depth decoder (0.6B)	same ladder (Q8_0 is the validated quality floor)
mm3-cond-f16.gguf	Condition encoder (25M)	f16 only — never quantised
mm3-voc-f16.gguf	Vocoder (54M)	f16 only — never quantised
LICENSE	MiniMax-Music3 Community License (governs the weights)	—

Suggested combos: quality = everything f16 (24 GB VRAM); recommended = LM/DiT/depth q8_0 + f16 frontends (13 GB); balanced = LM q8_0 + DiT Q4_K_M + depth q8_0 (~12 GB download, the split's headline mix); fast on RTX 50-series = LM/DiT NVFP4 + depth q8_0. Audio-code LMs degrade audibly below Q5 — the sub-Q5 LM files exist for experiments, not listening.

The legacy two-file layout (mm3-synth-<quant>.gguf bundling depth+cond+dit+voc) remains available for older HOT-Step versions; current versions load either, preferring split files.

Output: 44.1 kHz stereo, up to 5 minutes.

Conversion provenance

Converted with HOT-Step's engine/tools/convert-mm3.py from the bf16/fp16 safetensors published by MiniMax (via the Comfy-Org repackage), then split per component with engine/tools/split-mm3.py (byte-exact tensor passthrough — a split file's tensors are bit-identical to the bundle's). 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). The split-model approach follows ServeurpersoCom/minimaxmusic.cpp, whose author kindly sanctioned reuse of his design.

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.