고정된 트윗
NVIDIA AI
13K posts
NVIDIA AI 리트윗함
What are people using to run local inference on DGX Spark?
ollama? LM Studio? vLLM? sgLang? TRT-LLM?
Do you run in Docker?
@TheAhmadOsman @AlicanKiraz0 @spark_arena @NVIDIAAI @NVIDIARTXSpark
English
Congrats to the @MiniMax_AI team on the release of MiniMax M3, a long-context multimodal model for text, image, and video reasoning. 🙌
Try it today with our free GPU-accelerated endpoint on build.nvidia.com.
Details: nvda.ws/4v4BWhD
MiniMax (official)@MiniMax_AI
MiniMax M3, Open-Weight, Now On Hugging Face , with only ~428B parameters and ~23B activated parameters Weights: huggingface.co/MiniMaxAI/Mini… MiniMax Sparse Attention: huggingface.co/papers/2606.13…
English
English
The fastest reasoning LLM is now in production on Baseten.
Mercury 2 is a diffusion LLM, so it generates tokens in parallel and hits 1,000+ tokens/sec on @NVIDIAAI GPUs, speeds that used to require specialized hardware.
@augmentcode is already using Mercury 2, cutting cost 90% and latency 82%.
Proud to partner with the @baseten team to bring dLLMs to production.
Baseten@baseten
We are excited to announce that we have partnered with @_inception_ai to make Mercury 2 available on Baseten. This makes us the first inference platform to bring Inception’s diffusion LLM to production. Inception’s dLLM architecture fixes the bottlenecks of sequential token generation and can deliver 1,000+ tokens/sec on standard NVIDIA GPUs. Early users like @augmentcode have seen impressive results, such as an 82% reduction in latency and 90% cost savings, while maintaining high quality.
English
@recursive_wave 🤣 you'll still make people jealous with those stacks though
English
Love seeing photos like this.
Let's see some more setups.
Curious what everyone's running these days. What models are you using and what are you building?
Alican Kiraz@AlicanKiraz0
4x Nvidia GB10 128GB, 400G QSFP-DD Switch, 2x QSFP-DD 400G to 2x200G QSFP cable and @NVIDIAAI Magic🔥🦾
English
We are also preparing an interactive session for our UE5 demo in SIGGRAPH 2026 Los Angeles 🌴🌴🌴. see you there! 🚀🚀🚀
NVIDIA AI@NVIDIAAI
One open model. 350,000+ motion clips. 15,000 FPS. MotionBricks from NVIDIA Research runs real-time character animation at scale, without hand-crafted transitions or fine-tuning. And yes, it works for robotics too. #SIGGRAPH2026 paper, demos + code: nvlabs.github.io/motionbricks
English
NVIDIA is coming to #SIGGRAPH2026 in Los Angeles 🌴
Neural rendering, world models, physical AI, hands-on labs, and more.
All the details 👉 nvidia.com/en-us/events/s…
English
One open model. 350,000+ motion clips. 15,000 FPS.
MotionBricks from NVIDIA Research runs real-time character animation at scale, without hand-crafted transitions or fine-tuning. And yes, it works for robotics too.
#SIGGRAPH2026 paper, demos + code: nvlabs.github.io/motionbricks
English
Shoutout to Caleb for putting together a great deep dive on Nemotron 3 🙌
Check it out.
Caleb Eom@calebfoundry
Nemotron 3 Full Breakdown With the help of Joey Conway from @NVIDIAAI getting into the specifics around why Nemotron 3 is kind of a big deal Biggest headline with Nemotron is: Hybrid Mamba Transformer, Latent MoE, and MTP Hybrid Mamba Transformer essentially attacks right at the Attention mechanism to make the overhead sub-quadratic, but unlike quantizing KV Cache or swapping out attention head, NVIDIA chose Mamba-2 Latent MoE helps further optimize on sparsity by down projecting the dimensions so you're doing less math and less memory movement between HBM and SRAM, you're saving a ton, and NVIDIA made a conscious choice to add more experts given the surplus Finally, MTP or multi token prediction where the model can see future tokens to be more expressive in training and also option to use for speculative decoding during inference Oh, also the model adopts the new OpenMDW 1.1 License
English
Generate Synthetic Data for Physical AI With NVIDIA Brev Launchables and Agent Skills x.com/i/broadcasts/1…
English
Fable tailored Reachy running locally on a DGX spark cluster is magical. 🌠
@NVIDIAAI @claudeai @pollenrobotics
English
Nemotron 3 Full Breakdown
With the help of Joey Conway from @NVIDIAAI getting into the specifics around why Nemotron 3 is kind of a big deal
Biggest headline with Nemotron is: Hybrid Mamba Transformer, Latent MoE, and MTP
Hybrid Mamba Transformer essentially attacks right at the Attention mechanism to make the overhead sub-quadratic, but unlike quantizing KV Cache or swapping out attention head, NVIDIA chose Mamba-2
Latent MoE helps further optimize on sparsity by down projecting the dimensions so you're doing less math and less memory movement between HBM and SRAM, you're saving a ton, and NVIDIA made a conscious choice to add more experts given the surplus
Finally, MTP or multi token prediction where the model can see future tokens to be more expressive in training and also option to use for speculative decoding during inference
Oh, also the model adopts the new OpenMDW 1.1 License
English
@Soveryn_AI Nice! Keep us posted once the Spark lands on your doorstep.
English
@NVIDIAAI waiting for my spark to arrive i am tying it to my main server with 3 gpus with 144 gb of vram should be epic
English
Excited to show results of the first steps towards automated AI research at @Recursive_SI. The same general system achieved state of the art on @NVIDIAAI's SOL-ExecBench GPU Kernel Optimization, nanoGPT Speedrun, and @karpathy's NanoChat autoresearch benchmarks.
English