Instructions to use koboldcpp/music with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use koboldcpp/music with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf koboldcpp/music:Q4_K_M # Run inference directly in the terminal: llama cli -hf koboldcpp/music:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf koboldcpp/music:Q4_K_M # Run inference directly in the terminal: llama cli -hf koboldcpp/music:Q4_K_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf koboldcpp/music:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf koboldcpp/music:Q4_K_M
Use Docker
docker model run hf.co/koboldcpp/music:Q4_K_M
- Llama new
- LM Studio
- Jan
- Ollama
How to use koboldcpp/music with Ollama:
ollama run hf.co/koboldcpp/music:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use koboldcpp/music with Docker Model Runner:
docker model run hf.co/koboldcpp/music:Q4_K_M
- Lemonade
How to use koboldcpp/music with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull koboldcpp/music:Q4_K_M
Run and chat with the model
lemonade run user.music-Q4_K_M
List all available models
lemonade list
- Atomic Chat
Commit History
8 days ago
-
Upload sheetsage2-orig.gguf
Verified signature155bad8
10 days ago
-
Upload YuE2-No-LLM.kcppt
Verified signatureaa21934 -
Update README.md
Verified signature27aee06
12 days ago
-
Upload 2 files
Verified signaturea51b39a
-
Upload acestep-v15-xl-sft-turbo60.gguf
Verified signature5f747e2
-
Upload 2 files
Verified signature7f8ae44 -
Upload acestep-v15-xl-turbo-Q8_0.gguf
Verified signature56232d5 -
Upload acestep-v15-xl-sftturbo50-Q6_K.gguf
Verified signature38a2161
-
Upload acestep-v15-xl-turbo-Q4_K_M.gguf
Verified signaturef192d50
-
Upload ace-step-sftturbo-6GB-1.7B.kcppt
Verified signature3f77ff9
-
Update README.md
Verified signature6f25e97 -
6GB 4B model - Tight fit, doesn't fit? Try the 4GB config
Verified signaturee9c8356 -
Ace Step 4GB vram config
Verified signature5c6724c -
Upload acestep-5Hz-lm-1.7B-Q8_0.gguf
Verified signature241cc07 -
6GB 1.7B model - Can't fit it? Use the 4GB config
Verified signature70d2e82
-
Upload acestep-5Hz-lm-4B-Q6_K.gguf
Verified signatured68d31e -
Got 8GB of vram? Pick this config
Verified signature8cd08fa
-
Upload acestep-v15-sftturbo50-Q8_0.gguf
Verified signaturefa4eb9d
-
Got 10GB of vram? Use this file to get setup
Verified signature2f39cc3 -
Reconverted in SFT mode & Add 4B LLM
Verified signatureBasically this merge model can be converted using either the turbo config or the sft config. I found the sft version to have better results especially at higher step counts, this lines up with my experiences in the gradio. It will still work with few steps in this mode.f4e90c2 -
Upload acestep-5Hz-lm-0.6B-BF16.gguf
Verified signaturebab7a3b -
Upload Ace-Qwen3-Embedding-0.6B-BF16.gguf
Verified signature8605e74 -
Upload Ace-Qwen3-Embedding-0.6B-Q8_0.gguf
Verified signaturea31d09e -
Create README.md
Verified signature83f9363 -
Upload ace-vae-BF16.gguf
Verified signaturebfad32c -
Upload acestep-v15-sftturbo50-Q8_0.gguf
Verified signature232ca92 -
Upload acestep-5Hz-lm-1.7B-BF16.gguf
Verified signature9193fcf -
Upload acestep-v15-sftturbo50-BF16.gguf
Verified signaturea3bc32b -
initial commit
Verified signature1cde37a