Run Starling LM 7B Beta on iPhone, iPad & Mac
General conversational and coding model trained with RLHF on Mistral 7B
Starling LM 7B Beta runs 100% private on iPhone, iPad & Mac inside Private LLM — no internet connection required, no data sent to any server.
Model on Hugging Face
Specifications
- Parameters
- 7.2B
- Context window
- 8K tokens
- License
- Apache 2.0
- Quantization
- OmniQuant 3-bit, OmniQuant 4-bit
- Family
- Mistral 7B
What Starling LM 7B Beta is good at
Trained with reinforcement learning from AI feedback, Starling LM 7B Beta is an open 7.2 billion parameter model built on the Mistral 7B family. It follows instructions reliably and draws on broad general knowledge from its fine-tuning. The model is especially effective at multi-turn conversations and coding tasks when used with its required “GPT4 Correct” or “Code” chat template. It scored 8.12 on the MT Bench evaluation with GPT-4 as a judge, reflecting strong helpfulness and harmlessness. The context window supports up to 8192 tokens.
Which of your devices can run it
iPhone
iPad
Mac
How to run Starling LM 7B Beta in Private LLM
- Download Private LLM from the App Store.
- Open the in-app model library and choose Starling LM 7B Beta.
- Download the model once, then chat fully offline.
Variants & related models
Airoboros M 7B
General instruction-following model built on Mistral with structured math output
BioMistral 7B
Survival-focused biomedical research model built on Mistral 7B Instruct
Cerbero 7B
Multilingual Italian comprehension and sentiment fine-tune of Mistral 7B
CodeNinja 1.0 OpenChat 7B
Code completion and refactoring specialist built on OpenChat 3.5
DictaLM 2.0 Instruct
Hebrew-first multilingual chat and translation model based on Mistral 7B
Frequently asked questions
Yes. Starling LM 7B Beta runs on iPhone models with enough memory, such as iPhone 17 Pro Max, iPhone 17 Pro, iPhone Air, iPhone 17, iPhone 16 Pro / 16 Pro Max, iPhone 16 / 16 Plus, iPhone 16e, iPhone 15 Pro / 15 Pro Max, iPhone 15 / 15 Plus, iPhone 14 / 14 Plus / 14 Pro / 14 Pro Max, iPhone 13 Pro / 13 Pro Max, iPhone 12 Pro / 12 Pro Max, fully on-device in Private LLM — no internet connection required.
Yes. Starling LM 7B Beta 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), Mac (Apple Silicon, 8GB), fully on-device in Private LLM.
Yes. Once downloaded in Private LLM, Starling LM 7B Beta 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 Starling LM 7B Beta 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 Starling LM 7B Beta 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 Starling LM 7B Beta's Hugging Face model card, released under the Apache 2.0 license. Private LLM ships its own quantized models, built with OmniQuant quantization tuned per model, and isn't affiliated with the model's authors.