阶跃星辰开放 Step 5 Preview 权重
#模型发布#开源生态#多模态
#模型发布#开源生态#多模态
#模型发布#开源生态#推理
#模型发布#开源生态#Agent
Congrats to StepFun on Step 5 Preview 🙌 Their largest open weights release. The 600B MoE model is built to handle agent tasks lasting up to 24 hours. The model runs at nearly 8K tokens/sec/GPU on NVIDIA GB300 using NVFP4. NVP4 checkpoint: https://t.co/poBcZXeWqY Deploy with @SGL_project - https://t.co/2iE8ytEk50 or @vLLM_project - https://t.co/PedItg9OR4 Post-train with NeMo Automodel: https://t.co/KxNt53Sb8k Run it with NVIDIA NIM using a single command: https://t.co/UOWllHNEMW
#行业动态#推理#部署/工程
Step 5 Preview is here. @StepFun_ai's new open-weights model sets a new Pareto frontier, matching Kimi K3 on the @ArtificialAnlys Intelligence Index! It’s built for long-horizon agent work, with frontier-level results on software engineering and professional knowledge work, especially finance. - 600B sparse MoE, 27B active per token - ~1/6 the cost per task of Claude Opus 5.5, per Artificial Analysis Now on Featherless, served at FP8. https://t.co/mznI5gFzHe
#行业动态#开源生态#部署/工程
#模型发布#多模态#推理
#模型发布#多模态#OpenAI
#模型发布#多模态#推理
#产品更新#多模态#推理
#模型发布#多模态#推理
Meet NVIDIA Nemotron 3.5 Super VL Our new open model combines reasoning and tool use with text, image, document, and video understanding for long-running AI agents. 120B total parameters with 12B active 🧵 https://t.co/BcbED05qSG
#模型发布#开源生态#端侧
Muse Spark Open -- weights releasing today -- runs great on new Mac Studios thanks to work with @johnternus and Apple. https://t.co/U2wJNrKBOg
#模型发布#多模态#开源生态
1/ muse spark open is the most capable US open-weight model to date. 816B total params, 42B active. 1M-token context. natively multimodal. built for coding and agentic work like long-horizon tasks, hard software engineering, multi-step reasoning. america! 🇺🇲 https://t.co/NjtOB7aY9D
#模型发布#开源生态#多模态
1/ muse spark open is the most capable US open-weight model to date. 816B total params, 42B active. 1M-token context. natively multimodal. built for coding and agentic work like long-horizon tasks, hard software engineering, multi-step reasoning. america! 🇺🇲 https://t.co/NjtOB7aY9D
#行业动态#开源生态#Agent
Muse Spark Open -- weights releasing today -- runs great on new Mac Studios thanks to work with @johnternus and Apple. https://t.co/U2wJNrKBOg
#模型发布#开源生态#编码
Meta released the weights of Muse Spark Open, on Huggingface, an 816B-parameter model built for coding and agentic work. The open version shares the same base model as Muse Spark 1.3, with additional safety post-training to resist misuse as a standalone model without system guardrails, reversing Meta’s first proprietary, closed-weight frontier model strategy from April. Each of its 62 layers holds 256 expert networks and routes every token through 8, so deployment needs the memory of an 816B-parameter model but runs at the speed of a 42B model. That storage bill explains the Apple tie-up, because the M5 Ultra pushes 1.2 TB/s of unified memory and a Mac Studio can carry up to 512GB. A 3-bit quant tested on a 512GB M3 Ultra took about 344 GB and ran at about 21 tok/s generation on a short prompt.
#模型发布#开源生态#端侧
Meet NVIDIA Nemotron 3.5 Super VL Our new open model combines reasoning and tool use with text, image, document, and video understanding for long-running AI agents. 120B total parameters with 12B active 🧵 https://t.co/BcbED05qSG
#产品更新#多模态#Agent
SGLang has Day-0 support for Ling-3.1-flash from @AntLingAGI! A 560B MoE hybrid reasoning model, 25B active, 1M context, built for real work: it turns a rough brief into a page, mobile UI, or interactive prototype. ✅ MXFP4 + block-FP8 quantization cuts weights from ~534GB to ~292GB, fitting on 4 Hopper GPUs ✅ Strong on real-world agent, office, and coding tasks, including GDPVal-AA, FrontierSWE, and Terminal-Bench 4.0. Get started with SGLang:
#行业动态#开源生态#部署/工程
🎉 Day-0 support for Ling-3.1-flash is here in vLLM! ~560B total parameters, ~25B active per token, and up to 1M context. From a rough brief to websites, mobile UIs, and interactive prototypes—serve it on your own infrastructure with vLLM. Congrats to @AntLingAGI!
#开源/仓库#部署/工程#开源生态
MiniCPM-V 4.7 is now open source on ModelScope: a 35B-A3B MoE multimodal model built to run on-device without compromising performance. Apache 2.0. 🤖 https://t.co/NwwbEXRXGg 📱 First open-source MoE with smooth, lossless on-device inference, running at 13+ tokens/s on iPhone 17 Pro Max. 🔥 New Pareto frontier: in Instruct mode, it reaches a higher overall score in less inference time than Qwen3.6 35B-A3B. ⚡ Mixed 4x/16x visual token compression lets developers balance visual detail and inference cost per task. 🛠️ Two sizes (35B-A3B and 1B) with FP8, GPTQ, AWQ, BNB, and GGUF variants. Works with SGLang, vLLM, llama.cpp, Ollama, SWIFT, and LLaMA-Factory. 💻 Runs on iOS, Android, and HarmonyOS, with day-0 support for Rockchip, Houmo, Intel, AMD, and Arm.
#开源/仓库#端侧#多模态