Run Llama 3.3 70B Euryale v2.3 on Mac
Roleplay-optimized Llama 3.3 70B with flexible persona handling
Llama 3.3 70B Euryale v2.3 runs 100% private on Mac inside Private LLM — no internet connection required, no data sent to any server.
Model on Hugging Face
Specifications
- Parameters
- 70.6B
- Context window
- 131K tokens
- License
- Llama 3
- Quantization
- OmniQuant 3-bit, OmniQuant 4-bit
- Family
- Llama 3.3 70B
What Llama 3.3 70B Euryale v2.3 is good at
Llama 3.3 70B Euryale v2.3 is a 70.6 billion parameter model fine-tuned directly on Llama 3.3 Instruct—without LoRA extraction—to focus on storytelling, roleplay, and long-form creative writing. It supports a 131,072-token context and was trained to handle varied creative personas and tones flexibly, making it a straightforward replacement for the earlier Euryale v2.2 with slight quality improvements. Recommended generation settings from the creator are a temperature of 1.1 and a min_p of 0.1 using the Llama 3 Instruct prompt format.
Which of your devices can run it
Mac
How to run Llama 3.3 70B Euryale v2.3 in Private LLM
- Download Private LLM from the App Store.
- Open the in-app model library and choose Llama 3.3 70B Euryale v2.3.
- Download the model once, then chat fully offline.
Variants & related models
EVA LLaMA 3.33 70B v0.1
Roleplay and creative writing specialist based on Llama 3.3 70B
Llama 3.3 70B Instruct Abliterated
Uncensored Llama 3.3 70B with abliterated refusal mechanisms
Cat Llama 3 70B Instruct
Immersive roleplay via strict prompt adherence, Llama 3 70B finetune
EVA D Qwen2.5 1.5B v0.0
Roleplay-focused distillation of Qwen 2.5 with 131K context
EVA Qwen2.5 14B v0.2
Roleplay and storytelling specialist fine-tuned from Qwen 2.5 14B
Frequently asked questions
Llama 3.3 70B Euryale v2.3 is too large for current iPhones. It runs on Mac with enough unified memory inside Private LLM, fully offline.
Yes. Llama 3.3 70B Euryale v2.3 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), fully on-device in Private LLM.
Yes. Once downloaded in Private LLM, Llama 3.3 70B Euryale v2.3 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 Llama 3.3 70B Euryale v2.3 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 Llama 3.3 70B Euryale v2.3 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 Llama 3.3 70B Euryale v2.3's Hugging Face model card, released under the Llama 3 license. Private LLM ships its own quantized models, built with OmniQuant quantization tuned per model, and isn't affiliated with the model's authors.