Image created with gemini-3.1-flash-image-preview with claude-sonnet-4-5. Image prompt: Using the provided reference image hoodornament.jpg, preserve the deep midnight navy car hood, chrome pedestal base, shallow depth-of-field sky background, and dramatic upward automotive photography angle exactly as shown. Replace only the Mercedes star with a single polished chrome compass rose hood ornament–four cardinal points radiating from a center disc, precisely machined metal with fine directional markings, mounted on the same pedestal at realistic ornament scale. Add bold white sans-serif display text reading QWEN across the upper portion of the image in clean automotive advertisement style.
i am actually still not over how Qwen as we knew it, one of the S tier Tigers, is over.
https://x.com/swyx/status/2033030744352993296
Oh wow, Mamba-3 is here! For me, the most interesting use case of Mamba and Mamba-likes are the recent transformer attention hybrid architectures (Qwen3.5, Kimi Linear, etc.) Would be interesting to swap Gated DeltaNet with Mamba-3 (which now also has RoPE) in next gen hybrids.
https://x.com/rasbt/status/2034088726997893168#m
I reverse engineered Qwen 3.5’s FP8 format, and provide a script to recreate it.
https://x.com/QuixiAI/status/2033419073401287156
Pretty proud of this one! 😎 Qwen 3.5 Max Preview just hit #3 in Math, Top 10 in Arena Expert, and Top 15 overall! We’re already back in the lab optimizing the preview experience. Even sharper performance coming soon–stay tuned! 🚀
https://x.com/Alibaba_Qwen/status/2034658901321560549
Qwen 3.5 Max Preview has landed in top 10 for Arena Expert and top 15 for Text Arena. It shows particular strength in Math. Highlights: – #3 Math – #10 Expert – #15 Text Arena – Top 20 for Writing, Literature & Language, Life, Physical, & Social Science, Entertainment, Sports,
https://x.com/arena/status/2034653740465336407
With the preview of Qwen 3.5 Max Preview by @Alibaba_Qwen, we’re looking back at past Qwen Max variants to see how far it has progressed. Where Qwen 3.5 Max sees the largest gains vs. Qwen 3 Max: – Text Overall (+45pts) – Creative Writing (+57pts) – Math (+49pts) –
https://x.com/arena/status/2034658045113065603
ScreenSpot-Pro, the GUI computer use benchmark is now on @huggingface 🏆 just added Qwen3.5 it takes 5th place, with specialist Holo2 family takes top ranks whoever builds next GUI model based on Qwen3.5 can top the leaderboard? 🔥
https://x.com/mervenoyann/status/2034265145158119642#m
Good news: I got Qwen3.5-397B-FP8 running on my 8x mi210 server. Bad news: at 6 tokens per second.
https://x.com/QuixiAI/status/2033342155414982952
Leave a Reply