Not Fable, not Astra, but a model with only 6B active parameters (!) We're adding generic networking support, soon. Roblox is cooked.
1、开源版本没有2k, 使用三方超分工具， 一个15秒的视频要几十分钟 2、提示词走qwen 3.8 27B越狱版，图片走qwen image 2.1本身也没有无限制，但是minimax H3会拒绝
＋ Gemini 3.8 Flash Lite TTS ＋ LTX-2.5 の実験。 ポイントは、 「声を先に確定させ、その音声の実際の長さに合わせて動画を作る」 なので、音声が動画内に全てきっちり入る。 IA2V（Image-and-Audio-to-Video） の第一弾実験、成功です。
UbaldoHervas . EL prompt es suyo. Todo IA local Qwen 3.8 27B FP8. Usa mi motor propio de videos , eso si. Pero es IA local... Prompt en comentario
Part 3 of turning cerebras + Alibaba_Qwen 3.8 27B into an autonomous OS: closed loop flight control.
Made with Terresect, Qwen 3.8 27b on RTX 6000. Progress is sloooowwww.
Not just better local ai, but better ai on cheap commodity hardware... We have made a lot of progress, a P100 GPU (~$100).
Qwen 3.8 27B, Kimi K3, Mimo V2.6 flash and astra Xhigh. obviously astra won. Mimi was surprising. kimi did no audio and...qwen is qwen
Both decided to use Python with PIL and numpy. Much, much simpler, but Qwen's pretty decent for a 27b model, just hope it wasn't destroyed by…
The available models are listed as: • Claude Opus 5.5 • Claude Fable 5.1 • GPT-5.6 Sol • GPT-5.6 Luna • Grok 4.6 • Qwen 3.8 Max •
Yet another proof of concept. Don't judge it by the graphics quality/animation.
10 to 12 w per gpu at idle 30 to 35 w per gpu while it generates, peaks around 55 w never past 60°c on either box 45 tok/s fresh,
Bonsai2, a Qwen 3.8 27B model, running on 12GB VRAM -5 hours, 328k tokens, 2,368 lines GPU sitting in local computers is now a local coding agent.
The build is my octopus invaders prompt, which is open, and i'll leave the link below so you can reproduce it.