Developer Advocate @NebiusAI. Building with open models | coding agents | LLM inference
San Jose, CA, USA
Joined February 2025
- Tweets300
- Following534
- Followers287
- Likes493
Sujee Maniyam retweeted
🎂 I’m turning my dog into a video game for his second birthday!!
Tomorrow on Build With @nebiusai :
@sujee_dev tests AI models then we’ve got 30 minutes to build a game. You vote on the levels!
9 a.m. Pacific · X + YouTube. Let’s go!! 🔥
Sujee Maniyam retweeted
Join us on October 16 for a full day of technical workshops for AI builders and engineers.
→ Production-grade LLM inference with @nebiustf
→ Physical AI
→ Post-training
→ Onsite certification exams
Part of @nebiusai Build Week, leading up to #NVIDIAGTC Berlin.
Register: luma.com/nebius-academy-gtc2…
Sujee Maniyam retweeted
I was testing DeepSeek V4.1 Flash on @nebiustf , and honestly, the model is pretty damn good.
So I built a tiny real-time webcam app that takes multiple frames from the camera and uses the model to summarize what it sees.
The whole thing was surprisingly smooth, and the results were quite impressive for such a small setup.
Here’s a quick demo of it:
DeepSeek-V4.1-Flash is now live on Nebius Token Factory
The model comes with native image understanding plus an architecture built for faster inference and higher throughput on long, input-heavy workflows.
It combines native vision and a 1M token context with a 552B MoE that activates just 8B parameters for input and 16B for output.
Try it out: tokenfactory.nebius.com/?mod…
Sujee Maniyam retweeted
The Nebius AI Builder Program is now available.
AI isn’t just a model you call anymore. It’s a system you build. And builders, not a few closed labs, will decide what it becomes.
The open ecosystem has all the pieces. We want to make it easier to put them together and start building.
The program is free, with $400+ in credits and discounts, working code and cookbooks, office hours with engineers, and a community to build with.
We’re joined by @NVIDIAAI, @LangChain, @huggingface, @cognition, @OpenHandsDev, @tavilyai, @TolokaAI, @composio, @PrimeIntellect, @MiniMax_AI, @Alibaba_Qwen, and more joining soon.
Join with the link in the comments 👇
Sujee Maniyam retweeted
So much excitement about GLM-5.3-Flash, Kimi K3, and the pace of open models in general. But many of you are asking questions such as: does it beat what's serving in prod, will the tool calls parse in my agent loop, does latency hold when the context window fills up, can I post train it on my traces, and what's the $/token at real traffic
that's what we'll cover at Builders & Brews, plus a room full of people building on open models who are worth meeting.
Find your city: luma.com/g7vslxuv
Ox Alpha has a name: GLM-5.3-Flash.
@Zai_org’s new open-source model is now live on Nebius Token Factory on Day 0, with a 1M-token context window, multimodal capabilities, and zero data retention.
Build with it: tokenfactory.nebius.com/endp…
Sujee Maniyam retweeted
🚀 Token Factory Office Hour #4
Join us for a live, developer-focused session on @nebiustf
This time:
- Special guest Chris Alexiuk from NVIDIA, sharing insights on Nemotron models
- What’s new in Token Factory
- Builder demos
- Live Q&A - bring your questions
- Plus credits!
Calling all builders - built something cool with Token Factory and want to demo it? DM me!
Featured builders will receive Token Factory credits 🎁 to keep building.
📅 Wed, Aug 26, 2026
🕒 9 AM PDT / 12 PM ET / 6 PM CEST
💻 Online
Register: nebius.com/events/webinar-tf…
Sujee Maniyam retweeted
Qwen3.8-Max is coming to Nebius Token Factory on Day 0.
Great to kick things off together with Nebius as our Day 0 launch partner, bringing dedicated inference to more users.
Big model, right from the start.🔥@nebiustf
Qwen3.8-2.4T-A95B is going open weight: 2.4T parameters, with 95B active, and Nebius Token Factory is joining as a Day 0 launch partner.
Qwen3.8-2.4T-A95B is coming to Nebius Token Factory Managed Services for dedicated inference.
@Alibaba_Qwen @alibaba_cloud
Sujee Maniyam retweeted
Start building with Kimi K3 on Nebius Token Factory today with $25 in free credit.
Join the Nebius Builder Program and claim your $25 in free credit to start coding, test ideas, build prototypes, and see what Kimi K3 can do (program terms apply).
We can't wait to see what you build.
dev.nebius.com/builders?utm_…
Sujee Maniyam retweeted
Joined the first NEBIUS Fellows Office Hours and got a look at Kimi K3 on Token Factory 🔥
we're such nerds that while @sujee_dev was showing us around, we couldn’t stop thinking of experiments worth shipping
lowkey the most productive office hour ever
cc @Kimi_Moonshot @nebiusai
cc Fellows @rayyanzahidai @DhruvDiddi @troopdegen @tominerd @vivekhaldar and Ayub!
Sujee Maniyam retweeted
Kimi K3 is now available on Token Factory.
We’re excited to announce that Nebius Token Factory is an official Day 0 partner for @Kimi_Moonshot's Kimi K3.
Kimi K3 is the first open-weight model to reach frontier-level performance, a major step forward for open models.
It is built for long-horizon coding, knowledge work and reasoning, with native vision and up to 1M tokens of context. Artificial Analysis scores it at 57 on its Intelligence Index, just two points behind GPT-5.6 Sol (max). That puts Kimi K3 at the top of the open-weight field and firmly among today’s frontier models.
Developers can access K3 through Token Factory’s OpenAI-compatible API and console today.
Give K3 the hard problem.
Build with Kimi K3: tokenfactory.nebius.com/?mod…
Sujee Maniyam retweeted
Today we’re launching Custom Speculator Training in Nebius Token Factory.
Train workload-specific draft models from your own data and deploy them alongside the base model.
Generic drafters are a good start, but production traffic is rarely generic 👇
Sujee Maniyam retweeted
America's best open model shipped toda (550 billion parameters) and it's serving tokens on @nebiustf
Nemotron 3 Ultra is the most intelligent open-weights model the US has shipped. NVIDIA gave away the weights, the data, and the recipes. The intelligence is now a free, downloadable file. That is the headline, and it is real.
But a free file is not a product. This model was co-designed for NVFP4 on Blackwell. The thing that makes it fast is the format and the hardware path, and that only pays off on a serving stack tuned to exploit it. Download the weights and run them naive, you leave most of the model on the floor.
The work that turns the file into fast, cheap tokens is cache-aware routing, disaggregated prefill and decode, speculative decoding shaped to your traffic, dedicated capacity, regional isolation. The conversion layer. Nobody clones that in an afternoon.
That layer is what a token factory is. The model is the crude. The factory is the yield.
Nemotron 3 Ultra is live on Nebius Token Factory today, tuned to run the way NVIDIA built it to run. The weights are everyone's. The throughput is the part you come here for.
Jensen shipped the weights, we shipped the throughput.
NVIDIA Nemotron™ 3 Ultra is now live on Nebius Token Factory.
It’s built for long-running agents across coding, deep research and enterprise workflows.
Nemotron 3 Ultra delivers frontier reasoning with up to 5x faster inference and up to 30% lower cost for agentic workloads.
For builders, the next question is production: performance, reliability, economics and control.
Run it today: tokenfactory.nebius.com/mode…
Sujee Maniyam retweeted
🚀 New #1 on the @ArtificialAnlys Kimi K2.6 leaderboard: Eigen AI at 265 tok/s — in collaboration with @Nebius Token Factory. @nebiustf
On B200. Not GB300.
Topping the chart without Blackwell Ultra isn't a silicon story — it's a serving stack story. Every layer of EigenInference is co-designed for trillion-param MoE.
More coming 🔥
artificialanalysis.ai/models…
Sujee Maniyam retweeted
Headed to HumanX? Be sure to join our Masterclass Session on April 8 at 4:30 PM (Hall D-10) to break down the full engineering stack behind production LLMs.
📌 Plus don't miss:
• Live demos at our Booth #1127
• Meeting the team at our speakeasy
See you there!
Sujee Maniyam retweeted
I'm hiring a (US-based) Hackathons Lead to turn hackathons into a repeatable growth engine at @Nebius. Goal is not just more hackathons, it’s to systemize, scale and deliver the best hackathon program in the industry. If that's you (or know someone) pls DM or tag them here
Sujee Maniyam retweeted
“Nebius will take care of you,” — Jensen Huang, @NVIDIA’s Founder and CEO, in conversation with our CRO Marc Boroditsky at the Nebius booth here at #NVIDIAGTC.
We will.
Sujee Maniyam retweeted
Nebius.Build SF is coming to San Francisco on March 15 at Shack15.
A one-day, in-person builder event for engineers working on inference and robotics systems.
150+ AI builders. Two technical tracks. One full day of building.
What to expect:
- Token Factory workshop: run and optimize open-source models
- Robotics workshop: Cosmos-2 and GR00T VLA with real robots
- Hack sprint from 1:30 - 8:00 PM with demos and awards
- $25,000+ in prizes, including GTC passes
This is for teams pushing on latency, throughput, cost, reliability and real-world autonomy.
Fully in person. Space is limited. Teams of up to four.
Apply here: cerebralvalley.ai/e/nebius-b…
Sujee Maniyam retweeted
1/8 Training draft models for speculative decoding almost always relies on KL divergence – a proxy, that typically leads to convergence to suboptimal solutions under limited capacity. We introduce LK losses: training objectives that directly target acceptance rate instead.
We show consistent gains across 4 architectures and 6 target models (8B → 685B), up to 8-10% acceptance length, with zero added overhead.
arxiv.org/abs/2602.23881 🧵
Sujee Maniyam retweeted
Our Amsterdam HQ is officially open.
We welcomed the local team for Day 1 this week. Now it’s time for our global team to experience their first day in our new space.
Take a look inside our new home in Amsterdam. 👇
#LifeatNebius