Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Introducing NVIDIA Nemotron 3 Super 🎉 Open 120B-parameter (12B active) hybrid Mamba-Transformer MoE model Native 1M-token context Built for compute-efficient, high-accuracy multi-agent applications Plus, fully open weights, datasets and recipes for easy customization and deployment. 🧵

NVIDIA AI Developer

111,638 subscribers

135,302 views • 4 months ago •via X (Twitter)

News & Politics Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

✨ Meet our new open family of models: NVIDIA Nemotron 3 Open in weights, data, tools, and training, Nemotron 3 is built for multi-agent apps and features: • An efficient hybrid Mamba‑Transformer MoE architecture • 1M token context for long-term memory and improved reasoning • Multi‑environment reinforcement learning via NeMo Gym for advanced skill adaptation Plus NVFP4 pre-training, latent MoE, 1T tokens of data, and more. 📗Read the details in our tech blog: 🤗 Try the model on Hugging Face:

✨ Meet our new open family of models: NVIDIA Nemotron 3 Open in weights, data, tools, and training, Nemotron 3 is built for multi-agent apps and features: • An efficient hybrid Mamba‑Transformer MoE architecture • 1M token context for long-term memory and improved reasoning • Multi‑environment reinforcement learning via NeMo Gym for advanced skill adaptation Plus NVFP4 pre-training, latent MoE, 1T tokens of data, and more. 📗Read the details in our tech blog: 🤗 Try the model on Hugging Face:

NVIDIA AI Developer

68,886 views • 7 months ago

NVIDIA just released Nemotron 3 Ultra, a leading Hybrid Mamba-Transformer MoE open model for long-running agents. I've been test driving it these past few days, letting it work on Pi issues and it performed amazingly well! Update your and use it via OpenRouter today!

NVIDIA just released Nemotron 3 Ultra, a leading Hybrid Mamba-Transformer MoE open model for long-running agents. I've been test driving it these past few days, letting it work on Pi issues and it performed amazingly well! Update your and use it via OpenRouter today!

Mario Zechner

32,614 views • 1 month ago

Introducing NVIDIA Nemotron 3 Ultra. A frontier smart open model built for long-running agents that need to plan, reason, use tools and keep working across complex coding, research and enterprise workflows. Up to 5x faster inference and up to 30% lower cost for agentic tasks. Learn more:

Introducing NVIDIA Nemotron 3 Ultra. A frontier smart open model built for long-running agents that need to plan, reason, use tools and keep working across complex coding, research and enterprise workflows. Up to 5x faster inference and up to 30% lower cost for agentic tasks. Learn more:

NVIDIA

228,500 views • 1 month ago

🎉 Congrats to MiniMax (official) on releasing MiniMax M3! Frontier coding and agentic capabilities, native image and video input, computer use, and a 1M-token context window, all in a single open model. At the heart of M3 is MSA, a new sparse attention architecture: instead of attending densely over the full KV cache, each query scores 128-token KV blocks and runs attention only over the top blocks. That is what makes 1M-token context practical to serve. M3 runs in vLLM with day-0 support, verified on NVIDIA and AMD hardware: ✨ MSA sparse attention with dedicated prefill and decode kernels ✨ 1M-token context serving with prefix caching and chunked prefill ✨ BF16 and MXFP8 checkpoints, with MoE backends for both Hopper and Blackwell ✨ Native multimodal input (image + video) ✨ Tool calling, reasoning parsing, and thinking-mode control for agent workloads Day-0 support like this is a true team effort. Grateful to the teams at MiniMax (official), NVIDIA AI, AI at AMD, and Inferact, and to the vLLM community for making it happen. 🙏 Deep dive into the implementation, kernel work, and deployment recipes: 🔗

🎉 Congrats to MiniMax (official) on releasing MiniMax M3! Frontier coding and agentic capabilities, native image and video input, computer use, and a 1M-token context window, all in a single open model. At the heart of M3 is MSA, a new sparse attention architecture: instead of attending densely over the full KV cache, each query scores 128-token KV blocks and runs attention only over the top blocks. That is what makes 1M-token context practical to serve. M3 runs in vLLM with day-0 support, verified on NVIDIA and AMD hardware: ✨ MSA sparse attention with dedicated prefill and decode kernels ✨ 1M-token context serving with prefix caching and chunked prefill ✨ BF16 and MXFP8 checkpoints, with MoE backends for both Hopper and Blackwell ✨ Native multimodal input (image + video) ✨ Tool calling, reasoning parsing, and thinking-mode control for agent workloads Day-0 support like this is a true team effort. Grateful to the teams at MiniMax (official), NVIDIA AI, AI at AMD, and Inferact, and to the vLLM community for making it happen. 🙏 Deep dive into the implementation, kernel work, and deployment recipes: 🔗

vLLM

40,306 views • 1 month ago

🤝 Arcee.ai, an American AI lab, built its frontier open model family on NVIDIA Blackwell Ultra. Its flagship MoE model, Trinity-Large-Thinking, was RL post-trained using NVIDIA NeMo open libraries. Arcee optimized agentic model inference with NVIDIA Dynamo and vLLM, along with NVIDIA accelerated networking, to deliver low token cost, achieving: ✅ 3T+ tokens served on OpenRouter in its first two months ✅ $0.90 per 1M output tokens ✅ 2nd on PinchBench for open agentic models Explore Arcee's open models, powered by NVIDIA ➡️

🤝 Arcee.ai, an American AI lab, built its frontier open model family on NVIDIA Blackwell Ultra. Its flagship MoE model, Trinity-Large-Thinking, was RL post-trained using NVIDIA NeMo open libraries. Arcee optimized agentic model inference with NVIDIA Dynamo and vLLM, along with NVIDIA accelerated networking, to deliver low token cost, achieving: ✅ 3T+ tokens served on OpenRouter in its first two months ✅ $0.90 per 1M output tokens ✅ 2nd on PinchBench for open agentic models Explore Arcee's open models, powered by NVIDIA ➡️

NVIDIA AI Infrastructure

25,716 views • 3 days ago

Qwen just quietly dropped the most dangerous open model of 2026 Qwen3.6-Plus. native 1M context. agentic workflows. multimodal. half the size of competitors. and it's free on OpenRouter right now. you're not ready for this breakdown 🧵

Qwen just quietly dropped the most dangerous open model of 2026 Qwen3.6-Plus. native 1M context. agentic workflows. multimodal. half the size of competitors. and it's free on OpenRouter right now. you're not ready for this breakdown 🧵

Farhan

53,820 views • 3 months ago

Most capable generalist robotics models today are closed or at best, open weights. But robotics won’t reach its ChatGPT moment without real openness. That GPT moment was built on years of open tools and datasets such as Python, PyTorch, ImageNet and more, that let researchers inspect, reproduce, and build. Today, we’re introducing MolmoAct 2: a fully open-source action reasoning model for real-world robotics. We rethought and reshaped everything! 🧵👇

Most capable generalist robotics models today are closed or at best, open weights. But robotics won’t reach its ChatGPT moment without real openness. That GPT moment was built on years of open tools and datasets such as Python, PyTorch, ImageNet and more, that let researchers inspect, reproduce, and build. Today, we’re introducing MolmoAct 2: a fully open-source action reasoning model for real-world robotics. We rethought and reshaped everything! 🧵👇

Jiafei Duan

108,164 views • 2 months ago

Introducing Cosmos 3: Our latest frontier model for Physical AI Cosmos 3 is the world’s first fully open omnimodel with native vision reasoning, world and action generation. Today we’re releasing Super (32B) and Nano (8B) variants.

Introducing Cosmos 3: Our latest frontier model for Physical AI Cosmos 3 is the world’s first fully open omnimodel with native vision reasoning, world and action generation. Today we’re releasing Super (32B) and Nano (8B) variants.

NVIDIA AI

423,507 views • 1 month ago

NVIDIA Metropolis Blueprint for video search and summarization (VSS) 3 is here. Now your coding agent can analyze massive live streams and libraries of videos with a simple natural language prompt. Here's what's new: - 16 new agent skills: Search, summarize, alert, report, review clips. All from natural language prompts. - One unified open source repo: Source code, Docker and Helm deployment profiles for fast, easy deployment. - Multi-video reports and Nemotron 3 Nano Omni: Insights across video and audio at scale. - 3D multi-camera tracking: Production ready + #1 SOTA for smarter scene understanding. Try VSS skills 👉

NVIDIA Metropolis Blueprint for video search and summarization (VSS) 3 is here. Now your coding agent can analyze massive live streams and libraries of videos with a simple natural language prompt. Here's what's new: - 16 new agent skills: Search, summarize, alert, report, review clips. All from natural language prompts. - One unified open source repo: Source code, Docker and Helm deployment profiles for fast, easy deployment. - Multi-video reports and Nemotron 3 Nano Omni: Insights across video and audio at scale. - 3D multi-camera tracking: Production ready + #1 SOTA for smarter scene understanding. Try VSS skills 👉

NVIDIA AI

123,502 views • 24 days ago

🚨 Breaking: Google will soon launch Gemini CLI, a powerful open-source AI agent built for the terminal. - Built on Gemini 2.5 Pro - 1 million token context window - Free tier with 60 requests per minute and 1,000 per day - Google Search grounding for real-time context - Script and plugin support - Non-interactive mode for automation - Support for Model Context Protocol (MCP) - Integrated with Gemini Code Assist in VS Code - Fully open-source under Apache 2.0

🚨 Breaking: Google will soon launch Gemini CLI, a powerful open-source AI agent built for the terminal. - Built on Gemini 2.5 Pro - 1 million token context window - Free tier with 60 requests per minute and 1,000 per day - Google Search grounding for real-time context - Script and plugin support - Non-interactive mode for automation - Support for Model Context Protocol (MCP) - Integrated with Gemini Code Assist in VS Code - Fully open-source under Apache 2.0

AshutoshShrivastava

217,433 views • 1 year ago

Inside Nemotron and NVIDIA's AI lab: my conversation with Bryan Catanzaro (Bryan Catanzaro). NVIDIA is a chip company. So why does it put hundreds of researchers on building AI models - and then give them away for free? We go deep into the Nemotron models, what it takes to build a top AI lab, and the future of frontier AI. 01:33 - Is open source AI catching the frontier? 05:29 - Do closed labs blocking distillation slow open source down? 07:42 - Is the US falling behind China? 10:30 - Why companies actually choose open models 12:39 - A "crazy" 2008 bet: machine learning on GPUs 15:33 - Working with Andrew Ng and Dario Amodei at Baidu 17:41 - Coming back to NVIDIA: DLSS and the birth of Megatron 21:55 - The real reason NVIDIA builds its own models 24:28 - Is Moore's Law really dead? 33:37 - The Nemotron family: Nano, Super, Ultra 35:09 - Built for agents: why NVIDIA bets on speed 36:02 - How you train a 550B model in 4 bits 39:25 - Hybrid Mamba-Transformer, explained simply 42:31 - Mixture of experts, and why NVIDIA built NVL72 around it 47:26 - Why a 1-million-token context window matters 49:26 - Multi-token prediction: how the model predicts 5 tokens at once 52:47 - Multi-teacher distillation: teaching one model from many 58:01 - Where reinforcement learning goes next 01:00:16 - Inside NVIDIA's research org: "the mission is the boss" 01:04:03 - How NVIDIA decides who gets the GPUs 01:10:53 - Why NVIDIA still feels entrepreneurial after 33 years 01:12:58 - Why Bryan doesn't believe in the singularity 01:17:50 - The AI backlash 01:19:18 - The controversial case: open AI is safer than closed

Inside Nemotron and NVIDIA's AI lab: my conversation with Bryan Catanzaro (Bryan Catanzaro). NVIDIA is a chip company. So why does it put hundreds of researchers on building AI models - and then give them away for free? We go deep into the Nemotron models, what it takes to build a top AI lab, and the future of frontier AI. 01:33 - Is open source AI catching the frontier? 05:29 - Do closed labs blocking distillation slow open source down? 07:42 - Is the US falling behind China? 10:30 - Why companies actually choose open models 12:39 - A "crazy" 2008 bet: machine learning on GPUs 15:33 - Working with Andrew Ng and Dario Amodei at Baidu 17:41 - Coming back to NVIDIA: DLSS and the birth of Megatron 21:55 - The real reason NVIDIA builds its own models 24:28 - Is Moore's Law really dead? 33:37 - The Nemotron family: Nano, Super, Ultra 35:09 - Built for agents: why NVIDIA bets on speed 36:02 - How you train a 550B model in 4 bits 39:25 - Hybrid Mamba-Transformer, explained simply 42:31 - Mixture of experts, and why NVIDIA built NVL72 around it 47:26 - Why a 1-million-token context window matters 49:26 - Multi-token prediction: how the model predicts 5 tokens at once 52:47 - Multi-teacher distillation: teaching one model from many 58:01 - Where reinforcement learning goes next 01:00:16 - Inside NVIDIA's research org: "the mission is the boss" 01:04:03 - How NVIDIA decides who gets the GPUs 01:10:53 - Why NVIDIA still feels entrepreneurial after 33 years 01:12:58 - Why Bryan doesn't believe in the singularity 01:17:50 - The AI backlash 01:19:18 - The controversial case: open AI is safer than closed

Matt Turck

56,250 views • 16 days ago

NVIDIA just released a new open source transcription model, Nemotron Speech ASR, designed from the ground up for low-latency use cases like voice agents. Here's a voice agent built with this new model. 24ms transcription finalization and total voice-to-voice inference time under 500ms. This agent actually uses *three* NVIDIA open source models: - Nemotron Speech ASR - Nemotron 3 Nano 30GB in a 4-bit quant (released in December) - A preview checkpoint of the upcoming Magpie text-to-speech model These models are all truly open source: weights, training data, training code, and inference code. This is a big deal! Jensen said in the CES keynote yesterday that he expects open source models to catch up to proprietary models this year in a number of categories. NVIDIA is putting their weight behind making this happen. (As Alan Kay said, the best way to predict the future is to invent it.) The code for this agent is open source too, of course. You can deploy it to production with Modal and Pipecat AI cloud, or run locally on an NVIDIA DGX Spark or RTX 5090.

NVIDIA just released a new open source transcription model, Nemotron Speech ASR, designed from the ground up for low-latency use cases like voice agents. Here's a voice agent built with this new model. 24ms transcription finalization and total voice-to-voice inference time under 500ms. This agent actually uses three NVIDIA open source models: - Nemotron Speech ASR - Nemotron 3 Nano 30GB in a 4-bit quant (released in December) - A preview checkpoint of the upcoming Magpie text-to-speech model These models are all truly open source: weights, training data, training code, and inference code. This is a big deal! Jensen said in the CES keynote yesterday that he expects open source models to catch up to proprietary models this year in a number of categories. NVIDIA is putting their weight behind making this happen. (As Alan Kay said, the best way to predict the future is to invent it.) The code for this agent is open source too, of course. You can deploy it to production with Modal and Pipecat AI cloud, or run locally on an NVIDIA DGX Spark or RTX 5090.

kwindla

274,403 views • 6 months ago

$Introducing SubQ - a major breakthrough in LLM intelligence. It is the first model built on a fully sub-quadratic sparse-attention architecture (SSA), And the first frontier model with a 12 million token context window which is: - 52x faster than FlashAttention at 1MM tokens - Less than 5% the cost of Opus Transformer-based LLMs waste compute by processing every possible relationship between words (standard attention). Only a small fraction actually matter. Subquadratic finds and focuses only on the ones that do. That's nearly 1,000x less compute and a new way for LLMs to scale.$

Introducing SubQ - a major breakthrough in LLM intelligence. It is the first model built on a fully sub-quadratic sparse-attention architecture (SSA), And the first frontier model with a 12 million token context window which is: - 52x faster than FlashAttention at 1MM tokens - Less than 5% the cost of Opus Transformer-based LLMs waste compute by processing every possible relationship between words (standard attention). Only a small fraction actually matter. Subquadratic finds and focuses only on the ones that do. That's nearly 1,000x less compute and a new way for LLMs to scale.

Alexander Whedon

13,189,665 views • 2 months ago

New course on serving LLMs efficiently -- how do you serve models to many concurrent users at low latency and reasonable cost? This short course is built with Red Hat and taught by Cedric Clyburn. Efficient LLM serving requires efficient memory management. A 70B-parameter model takes ~140 GB just to load the weights. On top of that, every active request needs its own chunk of GPU memory, the KV cache, to store the token context it has built up so far. In this course, you'll learn to reduce a model's memory footprint with quantization and serve it using vLLM, which handles many concurrent requests efficiently through smart memory management. Skills you'll gain: - Quantize a model and measure the accuracy tradeoff - Serve a model with vLLM and watch it handle concurrent requests efficiently - Benchmark your deployment and make informed tradeoffs between speed, cost, and accuracy Join and learn to serve LLMs efficiently:

New course on serving LLMs efficiently -- how do you serve models to many concurrent users at low latency and reasonable cost? This short course is built with Red Hat and taught by Cedric Clyburn. Efficient LLM serving requires efficient memory management. A 70B-parameter model takes ~140 GB just to load the weights. On top of that, every active request needs its own chunk of GPU memory, the KV cache, to store the token context it has built up so far. In this course, you'll learn to reduce a model's memory footprint with quantization and serve it using vLLM, which handles many concurrent requests efficiently through smart memory management. Skills you'll gain: - Quantize a model and measure the accuracy tradeoff - Serve a model with vLLM and watch it handle concurrent requests efficiently - Benchmark your deployment and make informed tradeoffs between speed, cost, and accuracy Join and learn to serve LLMs efficiently:

Andrew Ng

124,185 views • 1 month ago

Today we open-source LingBot-Video — the first MoE-based video foundation model built for embodied intelligence. 🔹30B params, only 3B active at inference. 🔹Augmented with 70K hours of embodied data on top of large-scale internet video pretraining. 🔹Already outperforming Wan2.6, Seedance 1.5 Pro, and Cosmos3 Super on RBench. 🧵👇

Today we open-source LingBot-Video — the first MoE-based video foundation model built for embodied intelligence. 🔹30B params, only 3B active at inference. 🔹Augmented with 70K hours of embodied data on top of large-scale internet video pretraining. 🔹Already outperforming Wan2.6, Seedance 1.5 Pro, and Cosmos3 Super on RBench. 🧵👇

Robbyant

1,170,962 views • 10 days ago

🚨 ALIBABA JUST OPEN-SOURCED THE MOST POWERFUL MODEL IN THE WORLD - Qwen3.5 plus And it changes the AI race forever. This is not another “bigger model” release. This is a complete architectural reset. 397B parameters → only 17B active at inference, Qwen3.5 plus delivers performance on par with GPT-5.2 and Gemini-3-Pro. A new Hybrid Sparse MoE + Linear Attention architecture + Multi-Token Prediction = near-instant long-context responses and massive speed gains. Built as a true native multimodal model, it doesn’t just chat it builds. With a single prompt: “Use the React framework to create a visually impressive Mapbox demo featuring locations in Beijing and Shanghai” it generates a live interactive 3D map UI, structured components, real layouts, and production-ready frontend logic. This is real agentic, multimodal coding not a static code block. MMLU-Pro: 87.8 GPQA: 88.4 IFBench: 76.5 ⚡ up to 8× faster inference And it’s fully open-sourced under Apache-2.0. No locked APIs. No restricted tiers. 201 languages supported bringing frontier AI to developers, startups, and researchers worldwide. The race is no longer about the biggest model. It’s about the most usable intelligence. Open source just entered the top tier.

🚨 ALIBABA JUST OPEN-SOURCED THE MOST POWERFUL MODEL IN THE WORLD - Qwen3.5 plus And it changes the AI race forever. This is not another “bigger model” release. This is a complete architectural reset. 397B parameters → only 17B active at inference, Qwen3.5 plus delivers performance on par with GPT-5.2 and Gemini-3-Pro. A new Hybrid Sparse MoE + Linear Attention architecture + Multi-Token Prediction = near-instant long-context responses and massive speed gains. Built as a true native multimodal model, it doesn’t just chat it builds. With a single prompt: “Use the React framework to create a visually impressive Mapbox demo featuring locations in Beijing and Shanghai” it generates a live interactive 3D map UI, structured components, real layouts, and production-ready frontend logic. This is real agentic, multimodal coding not a static code block. MMLU-Pro: 87.8 GPQA: 88.4 IFBench: 76.5 ⚡ up to 8× faster inference And it’s fully open-sourced under Apache-2.0. No locked APIs. No restricted tiers. 201 languages supported bringing frontier AI to developers, startups, and researchers worldwide. The race is no longer about the biggest model. It’s about the most usable intelligence. Open source just entered the top tier.

RAVI KUMAR SAHU

379,913 views • 5 months ago

Alibaba just dropped Qwen3.5-397B-A17B and there's a lot to unpack. 397B params, 17B active per forward pass. Sparse MoE done right. But the real story isn't the size—it's the architecture choices. The MoE Design Most MoE models feel like bolt-ons. Qwen 3.5's sparse activation is native—only 4.3% of parameters fire per token. That's how you get trillion-parameter-class performance without trillion-parameter inference costs. The 0.8 RMB/million tokens pricing isn't subsidized; it's structurally earned. Native Multimodal, Not Glued-On This is a vision-language model from the ground up. Heterogeneous architecture—separate processing pipelines for text, image, video that fuse early. Not a vision encoder slapped onto an LLM. The result: 90.8 on OmniDocBench, 79.0 on MMMU-Pro. Document understanding and visual reasoning without the usual brittleness. The Context Window Reality Qwen3.5-Plus (the hosted version) ships with 1M tokens by default. That's not a marketing number—they're actually positioning it for long-document workflows. With built-in adaptive tool use, it's clearly aimed at agentic automation, not just chat. What Actually Impressed Me • FP8 native pipeline: ~50% activation memory reduction • Async RL framework for continuous refinement—training and inference workloads separated • 201 languages (up from 119), 250k vocab for better low-resource encoding • Apache 2.0 license. Full weights on HuggingFace and ModelScope. The Benchmark Context 76.4 on SWE-bench Verified puts it in the range where it can handle real debugging workflows. 72.9 on BFCL v4 for agentic tool use. 88.4 on GPQA Diamond. These aren't SOTA in isolation, but the breadth is unusual—strong across reasoning, coding, multimodal, and agentic tasks. The Honest Caveat I haven't stress-tested the 1M context for needle-in-haystack retrieval yet. And "native multimodal" claims need real-world torture testing—PDFs with tables, charts, mixed layouts. Benchmarks are benchmarks. Bottom Line This isn't just another model release. It's a bet on efficient scale: big model capabilities, small active compute, open weights. At 1/18th the cost of Gemini 3 Pro, it's going to force pricing conversations across the board.

Alibaba just dropped Qwen3.5-397B-A17B and there's a lot to unpack. 397B params, 17B active per forward pass. Sparse MoE done right. But the real story isn't the size—it's the architecture choices. The MoE Design Most MoE models feel like bolt-ons. Qwen 3.5's sparse activation is native—only 4.3% of parameters fire per token. That's how you get trillion-parameter-class performance without trillion-parameter inference costs. The 0.8 RMB/million tokens pricing isn't subsidized; it's structurally earned. Native Multimodal, Not Glued-On This is a vision-language model from the ground up. Heterogeneous architecture—separate processing pipelines for text, image, video that fuse early. Not a vision encoder slapped onto an LLM. The result: 90.8 on OmniDocBench, 79.0 on MMMU-Pro. Document understanding and visual reasoning without the usual brittleness. The Context Window Reality Qwen3.5-Plus (the hosted version) ships with 1M tokens by default. That's not a marketing number—they're actually positioning it for long-document workflows. With built-in adaptive tool use, it's clearly aimed at agentic automation, not just chat. What Actually Impressed Me • FP8 native pipeline: ~50% activation memory reduction • Async RL framework for continuous refinement—training and inference workloads separated • 201 languages (up from 119), 250k vocab for better low-resource encoding • Apache 2.0 license. Full weights on HuggingFace and ModelScope. The Benchmark Context 76.4 on SWE-bench Verified puts it in the range where it can handle real debugging workflows. 72.9 on BFCL v4 for agentic tool use. 88.4 on GPQA Diamond. These aren't SOTA in isolation, but the breadth is unusual—strong across reasoning, coding, multimodal, and agentic tasks. The Honest Caveat I haven't stress-tested the 1M context for needle-in-haystack retrieval yet. And "native multimodal" claims need real-world torture testing—PDFs with tables, charts, mixed layouts. Benchmarks are benchmarks. Bottom Line This isn't just another model release. It's a bet on efficient scale: big model capabilities, small active compute, open weights. At 1/18th the cost of Gemini 3 Pro, it's going to force pricing conversations across the board.

Bo Wang

13,221 views • 5 months ago

Inkling, Thinking Machines' first open model, dropped today: 975B total / 41B active MoE, up to 1M context, reasoning natively over text, images, and audio. Serving and RL support are already live: you can run and shape it on an open stack, starting now. Day 0 support on SGLang SGLang and Miles RadixArk👇 - Inkling's new architecture (ShortConv, attention with relative positional embedding, shared expert sink MoE) is natively implemented and deeply optimized, with prefill full CUDA graph and MXFP8 KV cache - Full parameter and LoRA RL in a customized Megatron backend, train inference consistency via customized kernels, routing replay, and cross-runtime parameter synchronization - DFlash speculative decoding from Modal for low-latency serving Launching now, blog and cookbook in the comments ⬇️

Inkling, Thinking Machines' first open model, dropped today: 975B total / 41B active MoE, up to 1M context, reasoning natively over text, images, and audio. Serving and RL support are already live: you can run and shape it on an open stack, starting now. Day 0 support on SGLang SGLang and Miles RadixArk👇 - Inkling's new architecture (ShortConv, attention with relative positional embedding, shared expert sink MoE) is natively implemented and deeply optimized, with prefill full CUDA graph and MXFP8 KV cache - Full parameter and LoRA RL in a customized Megatron backend, train inference consistency via customized kernels, routing replay, and cross-runtime parameter synchronization - DFlash speculative decoding from Modal for low-latency serving Launching now, blog and cookbook in the comments ⬇️

LMSYS Org

130,409 views • 3 days ago

NVIDIA JUST FEATURED HERMES AGENT AT COMPUTEX 2026. Hermes is integrating with NVIDIA OpenShell and Microsoft security primitives for secure on-device agents on Windows. Dillon Rolnick, CEO of Nous Research: "RTX Spark and NVIDIA OpenShell give Hermes users a powerful and secure environment for agents to run and work alongside you. You realize you're buying a full-fledged assistant, not a typical laptop." RTX Spark specs: → 1 petaflop AI performance → 20-core Grace CPU (built with MediaTek) → Blackwell GPU, 6,144 CUDA cores → 5th gen Tensor Cores with FP4 precision → up to 128GB LPDDR5X unified memory, 300 GB/s → NVLink C2C chip-to-chip interconnect → runs 120B parameter LLMs locally → up to 1M token context window on device → 2x inference speed via multi-token prediction RTX Spark devices ship Fall 2026 from ASUS, Dell, HP, Lenovo, Microsoft Surface, MSI. full NVIDIA press release in the comments. full Hermes setup guide in the article 👇

NVIDIA JUST FEATURED HERMES AGENT AT COMPUTEX 2026. Hermes is integrating with NVIDIA OpenShell and Microsoft security primitives for secure on-device agents on Windows. Dillon Rolnick, CEO of Nous Research: "RTX Spark and NVIDIA OpenShell give Hermes users a powerful and secure environment for agents to run and work alongside you. You realize you're buying a full-fledged assistant, not a typical laptop." RTX Spark specs: → 1 petaflop AI performance → 20-core Grace CPU (built with MediaTek) → Blackwell GPU, 6,144 CUDA cores → 5th gen Tensor Cores with FP4 precision → up to 128GB LPDDR5X unified memory, 300 GB/s → NVLink C2C chip-to-chip interconnect → runs 120B parameter LLMs locally → up to 1M token context window on device → 2x inference speed via multi-token prediction RTX Spark devices ship Fall 2026 from ASUS, Dell, HP, Lenovo, Microsoft Surface, MSI. full NVIDIA press release in the comments. full Hermes setup guide in the article 👇

YanXbt

45,809 views • 1 month ago

NVIDIA is giving away free access to 130+ AI models for a full year > most people building AI agents are paying $50-200/month for API access NVIDIA just made that argument irrelevant models you get: MiniMax M2.7, GLM 5.1, Kimi 2.5, DeepSeek-v4-flash, GPT-OSS-120B and 110+ more setup: > step 1 - get your free key > go to > register -> bind phone -> copy API key > step 2 - add to Hermes agent > open Settings -> Model Provider -> Custom base_url = " api_key = "nvapi-xxxxxxxxxxxxxxxxxxxx" > step 3 - pick a model model = "minimaxai/minimax-m2.7" model = "zhipuai/glm-5.1" model = "moonshot-ai/kimi-2.5" model = "deepseek-ai/deepseek-v4-flash" model = "nvidia/nemotron-3-ultra-550b-a55b" > Hermes already has NVIDIA set as default base_url > paste the key and you're running instantly > works the same in Cursor and OpenCode > cost: $0 > limit: 40 req/min > expires: 1 year while everyone is paying for API access, this is sitting there for free

NVIDIA is giving away free access to 130+ AI models for a full year > most people building AI agents are paying $50-200/month for API access NVIDIA just made that argument irrelevant models you get: MiniMax M2.7, GLM 5.1, Kimi 2.5, DeepSeek-v4-flash, GPT-OSS-120B and 110+ more setup: > step 1 - get your free key > go to > register -> bind phone -> copy API key > step 2 - add to Hermes agent > open Settings -> Model Provider -> Custom base_url = " api_key = "nvapi-xxxxxxxxxxxxxxxxxxxx" > step 3 - pick a model model = "minimaxai/minimax-m2.7" model = "zhipuai/glm-5.1" model = "moonshot-ai/kimi-2.5" model = "deepseek-ai/deepseek-v4-flash" model = "nvidia/nemotron-3-ultra-550b-a55b" > Hermes already has NVIDIA set as default base_url > paste the key and you're running instantly > works the same in Cursor and OpenCode > cost: $0 > limit: 40 req/min > expires: 1 year while everyone is paying for API access, this is sitting there for free

Mr. Buzzoni

192,952 views • 1 month ago