Tailor-made inference for your usecase
San Francisco
Joined April 2024
- Tweets66
- Following118
- Followers283
- Likes69
Kimi K3.1 Pro is live on Simplismart
@Kimi_Moonshot's 2.8T open model is now within 0.7 points of Opus 5.5 on Terminal-Bench, and leads on SWE Marathon and BrowseComp
Run it on dedicated GPUs, on our cloud or inside your own AWS, GCP or Azure, tuned to your workload
Full breakdown: simplismart.ai/blog/kimi-k3-…
Come join us today at 5–6 PM IST
Register here: luma.com/6uhcmz3l
Build it. Buy it. Or wait for it?
🗓 Wed, 4 Nov · 5–6 PM IST
Register: luma.com/6uhcmz3l
Every CTO is facing the voice AI question this year. Get it wrong and you lose a year of engineering, get locked into a stack, and watch customers hang up on a slow agent.
So we're putting two CTOs who run voice AI at scale on the same stage:
Devansh Ghatak, Co-founder & CTO, @SimplismartHQ
Prateek Sachan, CTO, @bolna_dev (YC F25)
What we'll get into:
→ Which build-vs-buy assumptions broke in the last 12 months
→ What two of India's biggest voice platforms actually see in production
→ Who owns voice, what gets measured, and how pilots become scale
→ The 2027 call: does the voice stack collapse into one model?
→ Your questions, live!
2
87
Simplismart retweeted
Build it. Buy it. Or wait for it?
🗓 Wed, 4 Nov · 5–6 PM IST
Register: luma.com/6uhcmz3l
Every CTO is facing the voice AI question this year. Get it wrong and you lose a year of engineering, get locked into a stack, and watch customers hang up on a slow agent.
So we're putting two CTOs who run voice AI at scale on the same stage:
Devansh Ghatak, Co-founder & CTO, @SimplismartHQ
Prateek Sachan, CTO, @bolna_dev (YC F25)
What we'll get into:
→ Which build-vs-buy assumptions broke in the last 12 months
→ What two of India's biggest voice platforms actually see in production
→ Who owns voice, what gets measured, and how pilots become scale
→ The 2027 call: does the voice stack collapse into one model?
→ Your questions, live!
Simplismart retweeted
Build, buy, or wait? What's the right call for voice AI? 🎙️
On Nov 4, we're getting Devansh Ghatak (Co-founder & CTO, @SimplismartHQ) and @xan_ps (Co-founder & CTO, @bolna_dev) together to talk about this.
What's worth building in-house, what makes more sense to buy, and what has changed after running voice AI in production?
Bring your questions too!
📅 Nov 4 | 5–6 PM IST
(registration link shared in comments)
Build it. Buy it. Or wait for it?
🗓 Wed, 4 Nov · 5–6 PM IST
Register: luma.com/6uhcmz3l
Every CTO is facing the voice AI question this year. Get it wrong and you lose a year of engineering, get locked into a stack, and watch customers hang up on a slow agent.
So we're putting two CTOs who run voice AI at scale on the same stage:
Devansh Ghatak, Co-founder & CTO, @SimplismartHQ
Prateek Sachan, CTO, @bolna_dev (YC F25)
What we'll get into:
→ Which build-vs-buy assumptions broke in the last 12 months
→ What two of India's biggest voice platforms actually see in production
→ Who owns voice, what gets measured, and how pilots become scale
→ The 2027 call: does the voice stack collapse into one model?
→ Your questions, live!
Introducing the Simplismart Python SDK + AI-agent skill:
• Import any GenAI model
• Compile on Simplismart Infra
• Deploy with autoscaling
• Use with Python, CLI, or AI agents like Claude Code
Read the deep dive 👇 simplismart.ai/blog/simplism…
1
5
1,135
🚀 We're excited to be a Day-0 launch partner for NVIDIA Nemotron 3 Ultra.
Deploy NVIDIA's latest open model for agentic AI on Simplismart
Our optimizations we deliver higher throughput than TensorRT + MTP + NVFP4.
Read more: lnkd.in/g7BrrNhy
#NVIDIA #Nemotron
Qwen3-TTS on Simplismart: 90ms TTFB in production ⚡
• 10 languages, 9 speakers
• Production-ready Voice AI: Built for agents, IVR, real-time dubbing
• Open-weight: your data never leaves your infrastructure
Read the deep dive ⬇️
#TTS #VoiceAI simplismart.ai/blog/qwen-3-t…
3
532
FLUX.2 [klein] is now on Simplismart 🚀
• ~1.3s inference (8.92× faster than the original)
• Text-to-image + multi-reference editing in one API
• 9B model matching quality of larger ones
Read the deep dive 👇 simplismart.ai/blog/flux-2-k…
286
We thought inference puzzles would be a fun add-on at #NVIDIAGTC.
Turns out… it has become a crowd magnet 🧩
Engineers, founders, operators all trying to crack it.
Think you can solve it faster?
Come by Booth #731 and give it a shot.
4
195
In town for #NVIDIAGTC?
We’re teaming up with @DigitalOcean for the AI Inference Mixer, a curated evening on inference & production AI.
📍 Habana Cuba Patio (short walk from GTC)
🗓️ Mar 18
⏰ 5:30–8:30 PM PDT
More details here - luma.com/rbnvkuch
2
174
🚀 Big update: Simplismart is now available to cloud providers on NVIDIA stack as a fully integrable AI cloud abstraction layer.
cio.economictimes.indiatimes…
To know more, talk to us at Simplismart Booth #731 at NVIDIA GTC (March 16-19, San Jose).
@nvidia
2
153
This game changing development
1️⃣ enables cloud providers to leverage Simplismart-optimised models served via NIMs (NVIDIA Inference Microservices).
2️⃣ empowers AI builders to choose desired config(s) that are optimised for throughput, latency, cost & quality.
1
1
143
Join us for InferSights by Simplismart.ai, to learn how to automate invoice processing end-to-end using VLMs and n8n workflows. Build a real-world pipeline that extracts, validates, and structures invoice data at scale.
📅 12 Feb | 6:00 - 7:00 PM IST
