Discussion

• @alibaba_qwen @alibaba_qwen on x

  🚀 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, [image…

• @itspaulai Paul Couvert on x

  How is this even possible?! Qwen has released 4 new models and the 4B version is almost as capable as the previous 80B A3B one 🤯 And the 9B is as good as GPT OSS 120B while being 13x smaller! - They can run on any laptop - 0.8B and 2B for your phone - Offline and open source

• @karankendre Karan on x

  Me realising I can run these models locally on my M1 MacBook Air for free [video]

• @adrgrondin Adrien Grondin on x

  The new Qwen 3.5 by @Alibaba_Qwen running on-device on iPhone 17 Pro. Qwen 3.5 beats models 4 times its size, has strong visual understanding, and can toggle reasoning on or off. The 2B 6-bit model here is running with MLX optimized for Apple Silicon. [video]

• @ollama @ollama on x

  The Qwen 3.5 small model series is now available ollama run qwen3.5:9b ollama run qwen3.5:4b ollama run qwen3.5:2b ollama run qwen3.5:0.8b All models support native tool calling, thinking, and multimodal capabilities in Ollama.

• @jason @jason on x

  Holy shit, it's happening

• @justinlin610 Junyang Lin on x

  final shot. these are the small models that i told u!

• @nummanali Numman Ali on x

  The new Qwen on device models receiving praise from Elon These are densely intelligent and replace the need for APIs for general tasks Within a year these could be Opus level as further distillation and training techniques improve They can even be embedded in web apps [image]

• @rohanpaul_ai Rohan Paul on x

  Big leap for on-device AI. Here Qwen 3.5 2B (6-bit) running on iPhone 17 Pro, MLX-optimized. Outperforms models 4X its size with strong visual intelligence. Powerful AI, now truly mobile. Opportunity for so many new products. [video]

• @elonmusk Elon Musk on x

  @Alibaba_Qwen Impressive intelligence density

• @deryatr_ Derya Unutmaz on x

  Alibaba Qwen 3.5 AI models have become unbelievable for their size! Soon we will enter the age of intelligent devices, when eventually an Apple Watch will have the expertise of a PhD on any topic! Then imagine running your AI agents on Raspberry Pis with Qwen 3.5! Not far away!

• @alexfinn Alex Finn on x

  Do you understand what this means? Are you aware how much the world just changed? You can now run frontier intelligence on a potato Your $600 Mac Mini can now run unlimited super intelligence for free. No authoritarian AI companies can cut you off Do this immediately, no

• @abhijitwt Abhijit on x

  finally, we can run an LLM locally on a 1GB RAM old laptop for free [video]

• @cgtwts @cgtwts on x

  Qwen 3.5 Small models - fully open source - beats models 4x it's size - 9B model performs on par with GPT OSS 120B while being 13x smaller - outperforms Gemini 3 flash and Claude sonnet 4.5 on select benchmarks - runs on any laptop - even works on a phone - completely free. [vide…

• @cherry_cc12 Chen Cheng on x

  We just dropped the Qwen3.5 Small series — 0.8B / 2B / 4B / 9B 🚀 Small doesn't mean limited anymore. Would love to hear what you build with them 👀

• @slow_developer Haider on x

  INCREDIBLE qwen just dropped 4 new qwen3.5 small models: 0.8b, 2b, 4b, and 9b. looking at the benchmarks, they're now matching gemini 3 flash and sonnet 4/4.5 in about half the tests, even on vision this is a big deal. because you can now run them locally, and they're good [image…

• @udiwertheimer Udi Wertheimer on x

  china just mogged @AlexFinn they waited for him to spend his life savings on 317 mac studios with a combined 4.7 petabytes of vram and then they released frontier models that are small enough to run on a single potato

• @_tobiaslee Lei Li on x

  Qwen 3.5 small models (0.8B-9B) with base models released 🫡 A 4B multimodal model that runs on a single 4090 — this is what makes LLM research accessible to PhD students without GPU clusters. Open base models = real SFT/RL research, not just prompting chat models. Respect to

• @lioronai Lior Alexander on x

  Alibaba shipped four Qwen 3.5 small models with a trick borrowed from their 397B model: Gated DeltaNet hybrid attention. Three layers of linear attention for every one layer of full attention. The linear layers handle routine computation with constant memory use. The full

• @aakashgupta Aakash Gupta on x

  The Qwen 3.5 small model hype is getting ahead of itself. Yes, the 9B beats GPT-5 Nano by 13 points on MMMU-Pro (70.1 vs 57.2) and 30+ points on document understanding. Yes, it outperforms Qwen's own previous-gen 30B on most benchmarks at a third the size. The bar charts look

• @theahmadosman Ahmad on x

  INCREDIBLE Qwen 3.5 smalls are here - 9B - 4B - 2B - 0.8B All image-to-text & text-to-text Built to run locally The models > Qwen 3.5 9B/9B-Base > Qwen 3.5 4B/4B-Base > Qwen 3.5 2B/2B-Base > Qwen 3.5 0.8B/0.8B-Base Small. Dense. Opensource. The future is local, Buy a GPU [image]

• @furman Andrew Furman on x

  Ok the local models are here Qwen 3.5 small models feel so slick on Locally AI app on iPhone [image]