Ark
@quimedesu
SWE, Graphics and AI Researcher
LocalLLM, Deepwen 3.6
509 Following 792 Followers
Deepseek v4.1 flash has got a new update behind the scenes, @ItsmeAjayKV, @loktar00 and I believe in that.
A mysterious new model called space bunny alpha has appeared on OpenRouter, it is GLM again or Qwen4? that's the question. Rendering the Pagoda Universe.
30 Web Designs made with Ternary-Bonsai-2-27B-PTQ1_0
It's a 5.5Gib model that can fit in 8gb GPUs, it's derived from Qwen3.8-27B, it's not just Q1, it uses their custom ternary kernels to achieve a higher accuracy that would not be possible with standard quantization and it needs a custom fork to work.
Show more
Deepseek v4.1 flash, it has no vision yet but wow
