Kent Worcester

📣Meet Qwen3.7-Max — our latest flagship, made for the Agent Era. A versatile foundation for agents that actually get things done: 🧑‍💻 Coding agent, end to end. Frontend prototypes, multi-file refactors, real debugging — nails it. 🗂️ A reliable office and productivity assistant. Get your work done through MCP integrations and multi-agent orchestration. ⏱️ Long-horizon autonomy. 35 hours straight on a kernel optimization task — 1,000+ tool calls, zero hand-holding. 🔌 Scaffold-agnostic. Claude Code, OpenClaw, Qwen Code, or your own stack. Consistent reliability everywhere. API's up on Alibaba Model Studio. You can also take it for a spin on Qwen Studio. Go build something wild!🏃🏃‍♂️ 📖 Blog: qwen.ai/blog?id=qwen3.7 ✅ Qwen Studio: chat.qwen.ai/?models=qwen3.… ⚡️ API：modelstudio.console.alibabacloud.com/ap-southeast-1…

v nice UX @AcrossProtocol

Qwen3.6 now runs 2x faster with MTP GGUFs! Run locally on just 18GB RAM. ⚡️ MTP enables Qwen3.6 to generate ~1.4–2.2× faster with no accuracy change. Qwen3.6-27B MTP runs at 160 tokens/s. 35B-A3B reaches 240 t/s. GGUFs: huggingface.co/unsloth/Qwen3.… Guide: #mtp-guide" target="_blank" rel="nofollow noopener">unsloth.ai/docs/models/qw…

DFlash for Gemma 4: Up to 6x Faster. ⚡⚡ Great to see MTP land natively in Gemma 4 today. If you want to push it further, try DFlash — open source, same quality, more speed!! github.com/z-lab/dflash

Took it further with @omma_ai, (@splinetool ) now it works on video, and everything working in a Web Browser. Drop a video, Depth Anything v2 calculates the depth map frame by frame, and Three.js renders a fully lit 3D mesh in real time. Depth estimation on video in the browser +Automatic baking pass + Dynamic lighting reacting to the geometry #vibecoding #threejs #webgl

LTX HDR beta is now live. Every AI video model before this one output 8-bit SDR only. Fine for social clips. The format falls apart the moment you try to grade. Highlights clip. Shadows crush. AI footage won't composite cleanly against higher-bit-depth CGI. Resolution was never the real issue. Dynamic range was.

claude code when i ask for help in my iOS project

ComfyUI Panorama Stickersが更新。 ビデオサポート、180度・360度パノラマに対応。 LTX-2.3 360 VR LoRAのプレビュー機能強化。 将来の3DシーンサポートやパノラマIC-LoRA作成も展望。 内部構造の最適化も実施。フィードバック歓迎。 #ComfyUI #PanoramaStickers URLはリプ⬇️

Alongside the ReFocus IC-LoRA, I've also released Uncompress which removes mp4 compression artifacts. These IC-LoRAs are incredibly easy to train, any artist/studio can make their own powered with @ltx_model

We're delighted to announce that MiniMax M2.7 is now officially open source. With SOTA performance in SWE-Pro (56.22%) and Terminal Bench 2 (57.0%). You can find it on Hugging Face now. Enjoy!🤗 huggingface：huggingface.co/MiniMaxAI/Mini… Blog: minimax.io/news/minimax-m… MiniMax API: platform.minimax.io

MiniMax Music 2.6 is live. A few things worth knowing: 🎬 Original BGM in minutes No more hunting for "probably fine to use" tracks. Describe your scene, get something fully yours. 🎭 Structure that actually follows your prompt. You can now write "open with tension, build toward awakening, explode into triumph", and the model follows, beat by beat. For the first time, AI music generation feels less like rolling the dice and more like directing. 🎤 Intentional imperfection In lo-fi, indie folk, jazz — the breathiness that makes a track feel human, not generated. Also shipping with 2.6: → First audio in under 20s: write a prompt, take a breath, it's ready → Improved low-mid frequency response: tighter bass for House, Trap, Drum & Bass → Style transfer & remixing: reimagine your own melody in a completely different genre 14-day free global beta starts today (500 songs/day). 👉Try now: minimax.io/audio/music

« ce que tu me demandes est une refacto complète c’est un gros chantier, tu es sûr de vouloir commencer maintenant ? »

The day has arrived! New open source AI music generator even beats Suno Ace Step 1.5 XL full tutorial: youtu.be/UAlLD5fS7-c

Releasing FLUX.2 Small Decoder: a faster, drop-in replacement for our standard decoder. → ~1.4x faster → Lower peak VRAM - decode larger images without running out of memory → Minimal quality loss → Works with FLUX.2 out of the box Especially impactful for real-time and larger resolutions pipelines.

Claude + Seedance 制作 登录页 UI/UX 首页案例测试+ 视差PixiJS 或 GSAP将乌鸦、女孩、花枝切成不同图层，根据鼠标坐标偏移。 呼吸微动CSS Animation使用 transform: scale() 配合 ease-in-out 循环。景深变化WebGL / Canvas模拟镜头虚化（Blur）的动态转换，增加质感。

Open models aren't "almost there" anymore. Independent evals from @langchain confirm: MiniMax M2.7 matches closed frontier models on core agent tasks at ~20× cheaper, 2–4× faster. Full blog👇 linkedin.com/pulse/open-mod…

Let me local AI pill you: 1. It sucks compared to SOTA 2. It can’t code so well 3. It can be a good agent 4. It can be great at chat 5. It can be fine as a researcher 6. It can be a great automation engine 7. It can be tuned however you want 8. It teaches you how the sausage is made 9. It works on a plane, or in an outage 10. It costs your electric bill + hardware 11. It is better than the AI we gave up coding for a year or 2 ago. Local AI is self defence, it is a go kit, it is a rebalancing of power. It’s delusional to think it approaches or will ever approach SOTA, the scale of private labs blows anything you can get for less than 25k USD out the water. Local AI is a bet that prices won’t stay this low, that private corporations with closed source weights can’t be trusted to stay consistent. I am more than happy to rent a Ferrari for dirt cheap, but i should also have a beater Toyota if I can afford it. Local AI is the car I can depend on to be there tomorrow, something that’s mine.

@sterlingcrispin It's good tho

Have you tried the new local model? It's Gemma-4-31B-IT-NVFP4. It's literally Bonsai-8B-gguf. It's on Qwopus3.5-27B-v3-GGUF. It's Nemotron-Cascade-2-30B-A3B. It's literally Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled. You can probably find it on Trinity-Large-Thinking. Dude it's Qwopus3.5-9B-v3-GGUF. It's a gpt-oss-puzzle-88B original. It's on Qwen3.5-35B-A3B-APEX-GGUF. You can watch it on context-1. You can go to LFM2.5-350M and watch it. Log onto Bonsai-8B-mlx-1bit right now. Go to zeta-2. Dive into Qwen3-Coder-Next. You can Llama-3.3-70B-Instruct it. It's on Voxtral-4B-TTS-2603. Qianfan-OCR has it for you. gemma-4-26B-A4B-it has it for you.

cute

Yet another model to try 😩