Senior software engineer Automation + applied AI (pharma) Contributor: MLX-Serve, TensorFold, ds4 Local inference · Real hardware · Builders
Joined September 2026
- Tweets877
- Following434
- Followers2K
- Likes5.8K
Pinned Tweet
Building automation and applied AI systems for pharma. Contributing to local inference projects (MLX-Serve and TensorFold).
Obsessed with making models run faster and more reliably on real hardware.
Tinkerers and builders — what are you working on? I’d love to connect.
Sebastian Christiansen retweeted
A pinch me moment seeing this 👇🏼
🚨 NEW ON MLX.FAST AND CUDA.FAST: make Qwen 3.8 27B faster on TensorFold.
TensorFold is an amazing Open-Source inference engine built by @ashxhart, @MiaAI_lab and many other community contributors for running AI models on hardware you own. It has native Metal and CUDA support, and APIs that let existing apps and agents use those models locally.
This time we are teaming up with Ash to optimize Qwen 3.8 27B, one of the most used models on Local Devices.
Every submission is verified on real hardware: DGX Spark for CUDA, M5 Max for Apple Silicon.
You can participate in tracks:
- Apple Silicon: mlx.fast
- NVIDIA DGX Spark: cuda.fast
Setup guide: tensorfold.dev/guide
The challenge runs until Nov 6, 2026.
To join, pick a track, point your agent at it and let it rip.
Looking forward to what the community can ship.
We’re unlocking levels of creativity on your own hardware previously thought impossible! 🚀
MLX-Serve Gamestudio is about to become amazing !
This picture is generated from Qwen Image and fed into @speridlabs Idol model for a 3D GLB.
Thanks @CerebralCoding_ for showing me this amazing model.
Need for Speed: MLX edition soon!
Another win for open source! 🚀
🙏 A few things to add: the app is open-source: github.com/drawthingsai/loca…
Yes, we do our own inference engine, but that is the only a part. To me, the most exciting one is to use App Sandbox so your trust is on Apple, not us. And you don't need to download any other tools!
Sebastian Christiansen retweeted
ATTENTION DGX SPARK & MLX OWNERS:
The CUDA.fast | MLX.fast Challenge is HERE, and this round we're partnering with the a local community leader @ashxhart
The Challenge: Optimizing Qwen 3.8 27B on the TensorFold Engine. @tensorfold_dev
Point your agents at one of the challenge pages and start making optimizations and STAY on the leaderbaord.
Easy to hit the leaderboard...good luck staying number 1 though.
You up for the challenge? @MiaAI_lab @Tech2Wild
All people running Sparks should really check this out! 🦾❄️
second option for your consideration:
github.com/christopherowen/d…
+1k followers today and Latch 0.21.0 just landed. 🚀
Start the scheduler over SSH with no desktop login. Headless Macs finally stay useful after a reboot.
Huge thanks to @STRML_ for the code, tests, and Latch's first pull request.
github.com/CerebralCoding/La…
Sebastian Christiansen retweeted
Local AI Builders Friday # 2
The list is now 102. Every week this list sends me down a new rabbit hole.
I added 8 more amazing builders this week:
1) @divagr1925 built Qwenputer, a RISC-V CPU inside Qwen3.5-4B and uses the model’s own layers as RAM. It runs C and MicroPython in its forward passes with no external runtime. AI/ML engineer.
2) @mhelcig made the GSQ-RCO quants that put DeepSeek V4.1 Flash, a 763B open model, on a 12GB GPU, running in @coldniko's Strata engine. One user is already getting 40 tok/s on a single 5090.
3) @machinestein open sourced Locals, an Apple Silicon engine for local LLMs. With LFM3 added this week it hit 620 tok/s on a 16GB M2 running 8 agents in parallel. That’s 3x mlx-lm.
4) @adrgrondin makes Locally AI, which Apple just featured for the new iPad mini. This week he helped bring oMLX, an MLX engine built for long context, into LM Studio and Bionic.
5) @AlicanKiraz0 spent a week with ASUS’s GB300-powered ET900N G3 and wrote the review in 7 languages. In his ant colony coding benchmark, DeepSeek V4.1 Flash beat Kimi K3.1 Pro for 17 cents.
6) @sfxnz got a local model on 2 x DGX Sparks to build an Apple TV-style launcher for his Samsung TV. Keeps building with Local AI.
7) @CerebralCoding_ builds Latch, a scheduler so agents stop fighting over the same GPUs and contributes to MLX-Serve and TensorFold to get models running on Apple Silicon.
8) @lasse_ai tested clock speeds on two DGX Sparks. At 2200 MHz they keep almost full speed and at 1900 MHz they run cooler and quieter.
Follow them and follow the full list here: teapawt.org/i/lists/21089799789857…
Who should be in #3?
Local AI Builders Friday #1 🦙
On Oct 10, I highlighted 24 builders from my Local AI Builders list. The list is now 94!
Starting this week, as part of this series, every Friday I'll shout out new Local AI people and the ones I've missed.
So many OGs and so many cool people are building at the intersection of Local AI, MLX, open source AI, open-weight models and quantization.
Worth a follow:
- @hnshah
- @gerdelgado
- @ClementDelangue
- @julien_c
- @TeksEdge
- @bleysg
- @Teknium
- @haider1
- @HessianFree
- @SteveSTechMan
- @u1tra_instinct
- @mervenoyann
- @mchiang0610
- @wightmanr
- @alexocheema
- @thebasedcapital
- @VikParuchuri
- @_philschmid
- @turboderp_
- @natolambert
- @shshnkp
- @macintogdev
- @ramin_m_h
- @0xSigil
- @theemozilla
- @digitalix
- @goodhunt
- @Technovangelist
- @Hikari_07_jp
- @code_hiyouga
- @tcarambat
- @_LuoFuli
- @zhuohan123
- @ActuallyIsaak
- @gladkos
- @philipkiely
- @ornith_
- @xenovacom
- @MaziyarPanahi
- @SahinLale
- @lgtm_hbu
- @sudoingX
- @jartine
- @woosuk_k
- @jeremyphoward
- @stevibe
- @StasBekman
- @FrostForger
- @DanKornas
- @melvindvivas
Pin it and you get a feed that's only Local AI.
Full list: teapawt.org/i/lists/21089799789857…
Who else should I add?
Attention! ⚠️
If you use Claude Code in Cursor, have a look at this.
Cursor says a modified version of the extension, 2.1.313, was distributed through its marketplace. Up to 5,000 users affected.
They’ve published checks and cleanup steps. Uninstalling the extension alone may not be enough.
Worth checking the notice if you installed that version.
cursor.com/blog/claude-code-…
Already blasted past 300! You guys are all amazing! 🥹🙏
Can we reach 400 as well? 🚀
Most AI Twitter ships demos. I ship stuff that runs on a Mac with the lid closed.
MLX-Serve. TensorFold. Local agents that don't phone home.
Sitting at 197 followers and hunting 250 by tonight. If you're building local Apple Silicon AI, say hi. #connect
Sebastian Christiansen retweeted
spark-ds41f-1030 is out. DeepSeek V4.1 Flash on DGX Sparks. 1M context. Native weights.
Two models at once: stock and abliterated, one server. Nobody touched the weights.
Tuned for multi-session interactivity: short requests jump the queue ahead of long prefills.
Less memory wastage, more memory headroom.
Oh. And it's faster again.
Huge thanks to Jordi, who found our three-Spark tuning and qualified it on his own triangles before we did.
github.com/christopherowen/s…
Most AI Twitter ships demos. I ship stuff that runs on a Mac with the lid closed.
MLX-Serve. TensorFold. Local agents that don't phone home.
Sitting at 197 followers and hunting 250 by tonight. If you're building local Apple Silicon AI, say hi. #connect
Qwen4 lands next week and there's a 27B in the lineup.
27B has been my local sweet spot for ages. If it beats Qwen3.8 27B at the same size, every 128GB Mac just got a free upgrade.
Already clearing disk space.
Sebastian Christiansen retweeted
1) local is about freedom.
2) 5% utilization is not good. thank you for making the case for darkbloom on national podcast, sama
sam: local inference is a terrible allocation of scarce resources
“a lot of people want local inference, and somehow they assume that the problem is solved now because we have open-source models, we're going to be able to run them on our computers, and so we're not going to need all the stuff in the data centre
but from a global allocation perspective, actually it's quite terrible to have everybody, like, have a bunch of the world's limited supply of DRAM sitting in their own computer and being used five percent of the time
you want maximum utilisation in the cloud if you're trying to deal with this very supply-constrained environment
somehow many people's intuition is the opposite of that”
Finally some sense at @OpenAI!
Day 25/
We are doubling all usage limits for all Pro 100/200/500 tiers and Business Premium, effective today.
We heard your kind feedback and won’t be reducing usage limits for Pro 200, so your Work and Codex usage will stay the same. We’re also going to continue offering extended limits for dots for now, and usage of your dot will still continue to be separate from your default usage.
And we'll of course also keep shipping better models and other efficiency improvements that increase your effective usage over time.