Manoj Khilnani

Marketer @Qualcomm. One life many roles. Half-marathoner, rare books collector, ex-restaurateur +++. Views are personal.

[yags @yagilb]

The announcement of @nvidia's acquisition of @huggingface on the same morning that Claude, ChatGPT, and Grok are all down shows the importance of owning your AI. Glad we'll have such a strong open model ecosystem with nvidia and HF joining forces.

[Skyroot Aerospace @SkyrootA]

ORBIT ACHIEVED. 🚀

Vikram-1 Test Flight-1 has reached orbit. India's first privately developed orbital rocket has completed its final burn and injected its payloads into a ~450 km orbit, making India the third country in the world with private orbital launch capability.

History is made. 🇮🇳

#Vikram1 #JourneyToOrbit #SkyrootAerospace

[Manoj Khilnani @manojkhilnani]

@ollama @Nasdaq @Theoryvc @ttunguz Super awesome!!

[ollama @ollama]

Ollama is back in NYC today!

It's exciting to see more people and businesses realize the benefits of open models! Ownership. Affordable. Private.

Thank you @Nasdaq and the @Theoryvc team.

[Manoj Khilnani @manojkhilnani]

Many congratulations team @ollama proud of our partnership and milestones both teams have achieved together. Miles to go…

[ollama @ollama]

Big day for Ollama! When we started, open models and the open source AI ecosystem were in their early days with few believers.

Our belief in open source has never wavered.

With today's fundraising announcement and our 9M+ active builders, we’re ready to scale open models into AI that you can own.

All aboard open models!

🧵

[clem 🤗 @ClementDelangue]

A study from @Stanford showed that 71.3% of chatgpt queries could be accurately answered by a local model. I suspect a major part of enterprise AI workloads could be run locally too for free (compared to the massive costs of frontier API cost).

Also, it reduces the risk of these workloads being taken away from you because you own the models instead of renting them - which sounds like a good idea these days haha.

That's why we're introducing the ability for everyone to filter AI models on @huggingface based on your local hardware.

For me, there are 800k+ public models that fit on my M5 24GB and that I can use easily thanks to llamacpp.

Let's go local AI!

[Sanchit monga @sanchitmonga22]

.@liquidai LFM 2.5 230M running blazing fast on QHexRT, 100% on the @Qualcomm NPU

Public access via the @RunAnywhereAI app coming next week, stay tuned :)

[Manoj Khilnani @manojkhilnani]

@MisraNityanand Beautifully explained.

[Manoj Khilnani @manojkhilnani]

@sanchitmonga22 @Qualcomm @RunAnywhereAI @liquidai This is amazing @sanchitmonga22 100% NPU execution with no CPU fallback is 🚀

[Sanchit monga @sanchitmonga22]

QHexRT is live: the inference engine for @Qualcomm Hexagon NPUs from the @RunAnywhereAI team

100% on the NPU. No CPU fallback.
First model: @LiquidAI LFM 2.5 230M.

We’re the first to run LFM 2.5 230M fully on the Hexagon NPU day ONE.

#qhexrt #runanywhere #qualcomm #liquidai #npu

[Manoj Khilnani @manojkhilnani]

@shawnshenjx Love what you guys have been building and our partnership!

[Manoj Khilnani @manojkhilnani]

@felixrieseberg Up and running on my Snapdragon PC and honestly loving every bit of it. Shoutout to @felixrieseberg for the fast fix. Great work from the team!

[Manoj Khilnani @manojkhilnani]

@anvisha Mods

[Anvisha @anvisha]

We raised $7.5M to kill AI slop.

Introducing Moda: the world's first design agent with taste.

RT+ comment “Moda” and we’ll design your brand for FREE.

[Manoj Khilnani @manojkhilnani]

@nexa_ai @Qualcomm @Snapdragon Excited to see real world use cases/apps coming out of this program. The real unlock here is making on‑device AI accessible to developers—without months of hardware‑specific tuning. Love seeing progress that helps teams ship faster across @Snapdragon NPU, GPU, and CPU.

[Qualcomm @Qualcomm]

@nexa_ai Excited to keep pushing on‑device AI forward together. 🤝

[Manoj Khilnani @manojkhilnani]

What we set out to demonstrate through this programme was that on-device AI can move from possibility to practicality, with the NPU playing a critical role in running and managing AI workloads. That’s exactly what the participants have shown. Huge congratulations to all teams.

[LM Studio @lmstudio]

Learn more about this model release
https://t.co/2r4lNcnwBM

[Manoj Khilnani @manojkhilnani]

Looking forward to see the ideas turn into action/apps in coming days. All the best to the finalists.

[Manoj Khilnani @manojkhilnani]

@charliejhills LOCAL