Install from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf FenomAI/MiniMax-Music3:F16# Run inference directly in the terminal:
llama cli -hf FenomAI/MiniMax-Music3:F16Use pre-built binary
# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf FenomAI/MiniMax-Music3:F16# Run inference directly in the terminal:
./llama-cli -hf FenomAI/MiniMax-Music3:F16Build from source code
git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf FenomAI/MiniMax-Music3:F16# Run inference directly in the terminal:
./build/bin/llama-cli -hf FenomAI/MiniMax-Music3:F16Use Docker
docker model run hf.co/FenomAI/MiniMax-Music3:F16MiniMax-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.
- Downloads last month
- 133
16-bit
Model tree for FenomAI/MiniMax-Music3
Base model
MiniMaxAI/MiniMax-Music3
Install (macOS, Linux)
# Start a local OpenAI-compatible server with a web UI: llama serve -hf FenomAI/MiniMax-Music3:F16# Run inference directly in the terminal: llama cli -hf FenomAI/MiniMax-Music3:F16