ImpulseLeap/en60m

RWKV-7 60M Mobile Pretrained (English)

This is a pretrained language model based on the cutting-edge RWKV-7 architecture, optimized specifically for local fine-tuning and inference directly on your iPhone.

Thanks to its ultra-lightweight design and the linear complexity of the RNN-like RWKV architecture, it delivers high performance, low latency, and minimal power consumption, making it an ideal choice for edge computing on mobile devices.

---

📊 Model Specifications

Below are the key technical parameters used by the application to initialize the network and tokenizer:

Parameter	Value
Architecture	RWKV-7
Total Parameters	60M
Layers	18
Hidden Size	448
Vocab Size	16,000 (16k)
Tokenizer	BPE (Byte-Pair Encoding)
Primary Language	English
License	Apache 2.0

---

📱 On-Device Fine-Tuning & Inference on iPhone

This model is tailored to fit within the strict RAM constraints of iOS. A footprint of ~60 million parameters allows you to perform local fine-tuning and text generation without overwhelming the device's available memory.

Key Mobile Features:

• Low Memory Footprint: Easily fits into RAM, leaving plenty of headroom for the application's UI and system processes.
• Efficient BPE Tokenizer: A 16k vocabulary optimized specifically for fast, low-overhead English text processing on mobile processors.
• RWKV-7 Architecture Advantage: Combines the generation quality of Transformers with the computational efficiency of RNNs, preserving your iPhone's battery life during inference and training.

💡 Fine-Tuning Tip: When training inside the app, we recommend using compact text datasets (such as personal notes, specific documentation, or custom dialogue logs). Local training ensures absolute privacy — your data never leaves your device.

---

🔒 License

This model and its weights are distributed under the Apache 2.0 license. You are free to use, modify, and distribute it for both personal and commercial applications.

ImpulseLeap / Alexei Goncharov

www.impulseleap.com