Run XWin LM 13B on Mac
General instruction model fine-tuned with RLHF from Llama 2 13B
XWin LM 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 XWin LM 13B is good at
With a 91.76% win rate on AlpacaEval, XWin LM 13B was the top-performing 13B instruction-following model at its release. It is built on Llama 2 13B and fine-tuned with supervised training and reinforcement learning from human feedback. The model handles up to 4096 tokens of context and is particularly good at providing helpful, detailed responses in multi-turn conversations.
Which of your devices can run it
Mac
How to run XWin LM 13B in Private LLM
- Download Private LLM from the App Store.
- Open the in-app model library and choose XWin LM 13B.
- Download the model once, then chat fully offline.
Variants & related models
Mythomax L2 13B
Roleplay specialist merging Llama 2 understanding and writing models
Spicyboros 13B
Uncensored de-alignment finetune of Llama 2 13B for unrestricted tasks
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
Airoboros l2 7b 3.0
Instruction following specialist built on Llama 2 7B
Airoboros M 7B
General instruction-following model built on Mistral with structured math output
Frequently asked questions
XWin LM 13B is too large for current iPhones. It runs on Mac with enough unified memory inside Private LLM, fully offline.
Yes. XWin LM 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, XWin LM 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 XWin LM 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 XWin LM 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 XWin LM 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.