Ten AI retweetledi
Can you guess which one is @Alibaba_Qwen Qwen 3.5 2B and which one is @GoogleDeepMind Gemma 4 2B? Running locally on @get_ten_ai iOS app
English
Ten AI
8 posts
Ten AI
@get_ten_ai
100% Private, Free & Unlimited AI. No signups, No ads, No internet required. Chat with latest LLMs, Transcribe Private Calls, Translate Offline in 50+ Languages
Katılım Şubat 2026
30 Takip Edilen15 Takipçiler
Gemma 4 is now available on the Ten AI app! 🚀 Download the app and run it locally on your iPhone!
Google@Google
We just released Gemma 4 — our most intelligent open models to date. Built from the same world-class research as Gemini 3, Gemma 4 brings breakthrough intelligence directly to your own hardware for advanced reasoning and agentic workflows. Released under a commercially permissive Apache 2.0 license so anyone can build powerful AI tools. 🧵↓
English
@awnihannun The main bottleneck for phones is going to be efficient memory management for long context and thermal profile management. Fully on iPhone AI also loses on agency as it does not have access to code execution.
English
According to benchmarks Qwen3.5 4B is as good as GPT 4o.
GPT 4o came out ~2 years ago (May 2024).
Qwen 3.5 4B runs easily on modern mobile devices.
So the gap between frontier intelligence in a datacenter and running a model of equal quality on your iPhone could be 2-3 years. (Probably closer to 3 assuming Qwen3.5 4B is more benchmaxxed than 4o)
I don't expect the trend of increasing intelligence-per-watt to change. So in 2-3 years it's plausible we will be running GPT 5.x quality models on an iPhone. Pretty wild.
English
Most on-device AI apps aren’t useful. MLX by design hogs memory and iOS crashes the app on longer conversations. Ten AI is the most efficient private on-device AI super app built on a custom fork of llama.cpp. Qwen 3.5 4B with vision will only consume upto 1 GB memory with Ten AI
English
Qwen 3.5 2B and 4B coming to Ten AI app soon 🚀 Unlimited & free. 100% private chat with the most intelligent small models 🔥
Qwen@Alibaba_Qwen
🚀 Introducing the Qwen 3.5 Small Model Series Qwen3.5-0.8B · Qwen3.5-2B · Qwen3.5-4B · Qwen3.5-9B ✨ More intelligence, less compute. These small models are built on the same Qwen3.5 foundation — native multimodal, improved architecture, scaled RL: • 0.8B / 2B → tiny, fast, great for edge device • 4B → a surprisingly strong multimodal base for lightweight agents • 9B → compact, but already closing the gap with much larger models And yes — we’re also releasing the Base models as well. We hope this better supports research, experimentation, and real-world industrial innovation. Hugging Face: huggingface.co/collections/Qw… ModelScope: modelscope.cn/collections/Qw…
English
While @OpenAI and @AnthropicAI fight on the principles of showing ads, here is our 1 line privacy policy. NO signups, NO ads, NO subscriptions, NO internet required. Ten AI app runs latest 4B parameter models on your iPhone - efficiently. Chat, Transcribe, Translate & more.
English