Run Spicyboros 13B on Mac
Uncensored de-alignment finetune of Llama 2 13B for unrestricted tasks
Spicyboros 13B runs 100% private on Mac inside Private LLM — no internet connection required, no data sent to any server.
Model on Hugging Face
Specifications
- Parameters
- 13B
- Context window
- 4K tokens
- License
- Llama 2
- Quantization
- OmniQuant 4-bit
- Family
- Llama 2 13B
What Spicyboros 13B is good at
Spicyboros 13B is a Llama 2 13B model intentionally fine-tuned with “de-alignment” data, making it willing to generate toxic, profane, and otherwise NSFW content on request. It handles unrestricted and sensitive tasks that standard aligned models would refuse. Trained mostly on synthetic instruction-response pairs generated by airoboros, it offers a 4096-token context window and uses a simple chat format with separate system/user/assistant lines. The model is built for general-purpose use with heavy emphasis on instruction following, and it includes function-calling, chain-of-thought, and execution-planning examples in its training data.
Which of your devices can run it
Mac
How to run Spicyboros 13B in Private LLM
- Download Private LLM from the App Store.
- Open the in-app model library and choose Spicyboros 13B.
- Download the model once, then chat fully offline.
Variants & related models
Mythomax L2 13B
Roleplay specialist merging Llama 2 understanding and writing models
Synthia 13B 1.2
General-purpose Llama 2 fine-tune with guided reasoning and long conversations
Wizard LM 13B
General purpose instruction finetune of Llama 2 13B with coding strength
XWin LM 13B
General instruction model fine-tuned with RLHF from Llama 2 13B
Amoral Gemma 3 1B v2
Uncensored Gemma 3 1B finetune for neutral factual responses
DeepSeek R1 Distill Llama 8B Abliterated
Uncensored DeepSeek R1 Distill 8B via refusal abliteration
Frequently asked questions
Spicyboros 13B is too large for current iPhones. It runs on Mac with enough unified memory inside Private LLM, fully offline.
Yes. Spicyboros 13B runs on Macs with enough unified memory, such as Mac (Apple Silicon, 192GB), MacBook Pro (M4 Max, 128GB), Mac Studio / Pro (Apple Silicon, 96GB), MacBook Pro (M4 Max, 64GB), MacBook Pro (M4 Max, 48GB), MacBook Pro (M4 Max, 36GB), Mac (Apple Silicon, 32GB), MacBook Air (M4, 24GB), MacBook Air (M-series, 16GB), fully on-device in Private LLM.
Yes. Once downloaded in Private LLM, Spicyboros 13B runs 100% on-device — no internet connection, and nothing is sent to any server.
Private LLM is a one-time purchase with no subscription and no per-message cost. The models themselves are open source — once downloaded, they run offline with nothing to pay per use.
Why run Spicyboros 13B in Private LLM
Private LLM has run local AI on iPhone, iPad, and Mac since 2023, well before Apple Intelligence, LM Studio, Ollama, etc. existed. Inference happens on your device, so your Spicyboros 13B conversations never reach a server. The part most apps gloss over is quantization, and that is exactly where on-device quality is won or lost. Most llama.cpp and MLX wrappers ship the same off-the-shelf 4-bit RTN weights. Private LLM ships GPTQ and OmniQuant quantization, tuned per model, and our 3-bit OmniQuant models match or beat those 4-bit RTN builds on the same Apple Silicon. Run the same model both ways and you feel it in the first reply. See how our quantization works.
Specifications and summary come from Spicyboros 13B's Hugging Face model card, released under the Llama 2 license. Private LLM ships its own quantized models, built with OmniQuant quantization tuned per model, and isn't affiliated with the model's authors.