←back to thread

Show HN: Cactus – Ollama for Smartphones

(github.com)
217 points HenryNdubuaku | 1 comments | 10 Jul 25 19:20 UTC | HN request time: 0.221s | source

Hey HN, Henry and Roman here - we've been building a cross-platform framework for deploying LLMs, VLMs, Embedding Models and TTS models locally on smartphones.

Ollama enables deploying LLMs models locally on laptops and edge severs, Cactus enables deploying on phones. Deploying directly on phones facilitates building AI apps and agents capable of phone use without breaking privacy, supports real-time inference with no latency, we have seen personalised RAG pipelines for users and more.

Apple and Google actively went into local AI models recently with the launch of Apple Foundation Frameworks and Google AI Edge respectively. However, both are platform-specific and only support specific models from the company. To this end, Cactus:

- Is available in Flutter, React-Native & Kotlin Multi-platform for cross-platform developers, since most apps are built with these today.

- Supports any GGUF model you can find on Huggingface; Qwen, Gemma, Llama, DeepSeek, Phi, Mistral, SmolLM, SmolVLM, InternVLM, Jan Nano etc.

- Accommodates from FP32 to as low as 2-bit quantized models, for better efficiency and less device strain.

- Have MCP tool-calls to make them performant, truly helpful (set reminder, gallery search, reply messages) and more.

- Fallback to big cloud models for complex, constrained or large-context tasks, ensuring robustness and high availability.

It's completely open source. Would love to have more people try it out and tell us how to make it great!

Repo: https://github.com/cactus-compute/cactus

1. DarmokJalad1701 ◴[10 Jul 25 21:15 UTC] No.44525702[source]▶
I would say that while Google's MediaPipe can technically run any tflite model, it turned out to be a lot more difficult to do in practice with third-party models compared to the "officially supported" models like Gemma-3n. I was trying to set up a VLM inference pipeline using a SmolVLM model. Even after converting it to a tfilte-compatible binary, I struggled to get it working and then once it did work, it was super slow and was obviously missing some hardware acceleration.

I have not looked at OP's work yet, but if it makes the task easier, I would opt for that instead of Google's "MediaPipe" API.