Instructions to use baa-ai/Muse-Spark-Open-816B-A42B-RAM-365GB-GGUF 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 baa-ai/Muse-Spark-Open-816B-A42B-RAM-365GB-GGUF 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 baa-ai/Muse-Spark-Open-816B-A42B-RAM-365GB-GGUF:F16 # Run inference directly in the terminal: llama cli -hf baa-ai/Muse-Spark-Open-816B-A42B-RAM-365GB-GGUF:F16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf baa-ai/Muse-Spark-Open-816B-A42B-RAM-365GB-GGUF:F16 # Run inference directly in the terminal: llama cli -hf baa-ai/Muse-Spark-Open-816B-A42B-RAM-365GB-GGUF:F16
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 baa-ai/Muse-Spark-Open-816B-A42B-RAM-365GB-GGUF:F16 # Run inference directly in the terminal: ./build/bin/llama cli -hf baa-ai/Muse-Spark-Open-816B-A42B-RAM-365GB-GGUF:F16
Use Docker
docker model run hf.co/baa-ai/Muse-Spark-Open-816B-A42B-RAM-365GB-GGUF:F16
- Llama new
- LM Studio
- Jan
- vLLM
How to use baa-ai/Muse-Spark-Open-816B-A42B-RAM-365GB-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "baa-ai/Muse-Spark-Open-816B-A42B-RAM-365GB-GGUF" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "baa-ai/Muse-Spark-Open-816B-A42B-RAM-365GB-GGUF", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/baa-ai/Muse-Spark-Open-816B-A42B-RAM-365GB-GGUF:F16
- Ollama
How to use baa-ai/Muse-Spark-Open-816B-A42B-RAM-365GB-GGUF with Ollama:
ollama run hf.co/baa-ai/Muse-Spark-Open-816B-A42B-RAM-365GB-GGUF:F16
- Unsloth Desktop
- Pi
How to use baa-ai/Muse-Spark-Open-816B-A42B-RAM-365GB-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf baa-ai/Muse-Spark-Open-816B-A42B-RAM-365GB-GGUF:F16
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "baa-ai/Muse-Spark-Open-816B-A42B-RAM-365GB-GGUF:F16" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use baa-ai/Muse-Spark-Open-816B-A42B-RAM-365GB-GGUF with Docker Model Runner:
docker model run hf.co/baa-ai/Muse-Spark-Open-816B-A42B-RAM-365GB-GGUF:F16
- Lemonade
How to use baa-ai/Muse-Spark-Open-816B-A42B-RAM-365GB-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull baa-ai/Muse-Spark-Open-816B-A42B-RAM-365GB-GGUF:F16
Run and chat with the model
lemonade run user.Muse-Spark-Open-816B-A42B-RAM-365GB-GGUF-F16
List all available models
lemonade list
- Hermes Agent
How to use baa-ai/Muse-Spark-Open-816B-A42B-RAM-365GB-GGUF with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf baa-ai/Muse-Spark-Open-816B-A42B-RAM-365GB-GGUF:F16
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:9931/v1 hermes config set model.default baa-ai/Muse-Spark-Open-816B-A42B-RAM-365GB-GGUF:F16
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use baa-ai/Muse-Spark-Open-816B-A42B-RAM-365GB-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf baa-ai/Muse-Spark-Open-816B-A42B-RAM-365GB-GGUF:F16
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:9931/v1 \ --custom-model-id "baa-ai/Muse-Spark-Open-816B-A42B-RAM-365GB-GGUF:F16" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Muse-Spark-Open-816B-A42B โ 365GB (GGUF)
Mixed-precision quantized version of meta-models/Muse-Spark-Open-816B-A42B using a proprietary quantization method by baa.ai.
Per-tensor bit-width allocation via advanced sensitivity analysis and budget-constrained optimisation โ no calibration data required. Built at the efficiency knee (best quality-per-GB).
Built with Muse Spark Open.
Metrics
| Metric | Value |
|---|---|
| Size | 365 GB (365,128,224,439 bytes; 22 shards) |
| Average bits | 3.56 |
| Format | llama.cpp (GGUF), arch muse-spark |
| Architecture | MoE (816B total / 42B active; 256 routed experts, top-8, 4096-d expert latent; sliding-window + global attention) |
Routed experts Q3_K; attention Q8_0 (12 attn_q at Q6_K, one attn_v at F16); attention output gate and expert latent projections Q8_0; output and token-embeddings Q6_K; router, norms and residual gates F32. The per-tensor spec is included as spec_muse_spark_knee.txt.
Files
| File | Contents | Size |
|---|---|---|
Muse-Spark-Open-816B-A42B-RAM-local-knee-000{01..22}-of-00022.gguf |
Text model (shard 1 holds metadata and the chat template) | 365.1 GB |
mmproj-Muse-Spark-Open-816B-A42B-F16.gguf |
Vision + audio projector, F16 | 4.1 GB |
spec_muse_spark_knee.txt |
Per-tensor quantization spec | โ |
Requirements
llama.cpp build โฅ b11671 is required โ Muse Spark Open support (#30616) landed on 2026-10-15 and is not in Homebrew llama.cpp 0.6.0 or the v0.7.0 release. Build from source or use a newer release until downstream runtimes catch up.
Usage
git clone https://github.com/ggml-org/llama.cpp && cd llama.cpp
cmake -B build -DGGML_METAL=ON && cmake --build build -j --target llama-cli llama-server
hf download baa-ai/Muse-Spark-Open-816B-A42B-RAM-365GB-GGUF --include "*.gguf" --local-dir ./muse-spark-ram-365gb
# The model is split into 22 shards โ point -m at the first; llama.cpp loads the rest automatically
./build/bin/llama-cli -m ./muse-spark-ram-365gb/Muse-Spark-Open-816B-A42B-RAM-local-knee-00001-of-00022.gguf -p "Hello!" -n 256 -ngl 99 --jinja
Or via llama-server for an OpenAI-compatible HTTP API (add --mmproj for image and audio input):
./build/bin/llama-server -m ./muse-spark-ram-365gb/Muse-Spark-Open-816B-A42B-RAM-local-knee-00001-of-00022.gguf \
--mmproj ./muse-spark-ram-365gb/mmproj-Muse-Spark-Open-816B-A42B-F16.gguf \
--port 8080 -ngl 99 --ctx-size 8192 --jinja
For fast inference use a host with โฅ ~370 GB RAM/VRAM; otherwise it runs via mmap paging. The chat template is embedded (the current upstream template, including tool namespaces); reasoning effort is set per request with "chat_template_kwargs": {"reasoning_effort": "low" | "medium" | "high" | "xhigh"} (default xhigh). No importance matrix (imatrix) was used โ per-tensor sensitivity allocation provides the primary quality signal.
Smoke-tested on a 192 GB Apple M2 Ultra via mmap paging (CPU, -ngl 0): correct answers on factual, arithmetic and code prompts at ~1 tok/s generation and ~0.6 tok/s prompt processing. WikiText-2 perplexity was not measured โ the model does not fit in that host's memory.
License
Use of this model is subject to the Muse Spark Open license and its Usage Policy, both included in this repository. Products or services using it must display "Built with Muse Spark Open", and Model-as-a-Service providers above the license's revenue threshold need a separate agreement with Meta.
Quantized by baa.ai
Black Sheep AI Products
Black Sheep AI builds private AI with the Bounded AI Architecture (BAA): three layers, each bound to something you control, on infrastructure you control. Nothing leaves your boundary.
Ram (Reasoning Layer) โ Full-capability frontier models, shrunk to fit smaller GPUs with reasoning kept and certified. They rely strictly on your Data Modules for knowledge, so you swap the model as better ones ship.
Paddock (Knowledge Plane) โ Binds your Data Modules directly to the reasoning layer: one per topic, period, person, permission or tenant. Permission, freeze, hand back or delete each one on its own.
Watchman (GRC Layer) โ Governance, risk and compliance in a single, complete audit log: every module permission, every bind, every model's provenance. Five certificates before anything goes live.
Shepherd โ Takes a frontier model, compresses it into a Ram reasoning model, certifies it with Watchman, binds it to your Paddock, and deploys the Bounded AI Architecture to your infrastructure: your cloud, a Mac Studio, or an air-gapped facility.
Learn more at baa.ai โ Private AI for enterprises whose data cannot leave the building.
- Downloads last month
- 154
We're not able to determine the quantization variants.
Model tree for baa-ai/Muse-Spark-Open-816B-A42B-RAM-365GB-GGUF
Base model
meta-models/Muse-Spark-Open-816B-A42B