Building AI’s unified compute layer. We are hiring → modular.com/careers 🚀
- Tweets 1,346
- Following 2
- Followers 24,339
- Likes 913
This week in Chicago, Mojo found The Bean, ate a pretzel half its size, and got to hang out with the whole Modular team at our off-site.
Want to come to the next one? We're hiring across Engineering, Product Management, Customer Engineering, and Developer Relations: modular.com/company/careers
1
2
29
1,922
Headed to Santa Clara today for #AIInfraSummit?
Don’t miss @alisterburt's talk at 10:30 AM PT in Expo Theater 2: "Modular: Open Source, Open Cloud, Open Silicon."
Stop by the Qualcomm booth (#206) anytime this week during expo hall hours to chat with the Modular team and catch a Modular Cloud demo.
3
15
1,626
Hippocratic AI cofounders @munjalshah and @debo_datta_ on the latency problem, from the ModCon keynote: piped.video/watch?v=hUSMA2r2…
4
702
GLM-5.3 open weights are now public, and Modular Cloud has Day Zero support.
GLM-5.3 is the most capable open-weights model for coding, with a 50% improvement over GLM-5.2 on @Zai_org's Code Bench.
Try it today on Modular Cloud: console.modular.com/?utm_sou…
7
60
3,749
Modular's price-performance on @Zai_org's GLM-5.2 (Non-reasoning) lands right on the Pareto frontier in @ArtificialAnlys' latest benchmark: near-top speed without the near-top price tag.
We're just getting started, and we're ready for GLM-5.3. Expect to see a lot more incredible results. 🚀
2
11
102
7,950
We're the #1 trending repo on @github today.
The Mojo compiler went open source at ModCon this week, and developers noticed fast.
Thank you to everyone who joined us in person and online. If you missed the keynote, the full recording is live on our YouTube channel:
piped.video/4Hw7PeIsFPo
2
11
187
10,641
That's a wrap on #ModCon2026!
Mojo 1.0 shipped as open source, Modular Cloud launched, and several hundred engineers spent the day pondering the hardest problems in AI infrastructure.
Thank you to everyone who joined us in San Francisco and on the livestream.
Catch the replay on YouTube: piped.video/watch?v=Yvb_G2Dr…
And enjoy these super fun pics created at our FLUX booth!
1
5
72
4,075
In just a few minutes, @dylan522p and @_micah_h address the gap between the story the industry tells about AI progress and what their data shows, in our AI Analyst Perspectives fireside chat at #ModCon2026. Join the livestream and share your reactions in the chat:
piped.video/watch?v=Yvb_G2Dr…
3
20
1,879
TTune in live now: piped.video/watch?v=Yvb_G2Dr…
Right now: Modular Cloud Deep Dive - How do we achieve performance under the hood?
Up next: Five investors, thirty minutes, one question: where is AI infrastructure capital going next? GV, General Catalyst, DFJ, USIT, and M12 represented.
#ModCon2026
1
11
2,989
And if you want to dig deeper into the announcements we shared this morning, tune into the ModCon livestream and explore the full announcements blog:
Livestream: piped.video/watch?v=Yvb_G2Dr…
Blog: modular.com/blog/modcon-anno…
7
1,016
Today, we open sourced Mojo 🔥.
Announced just now during the ModCon keynote, effective immediately, Apache 2.0 License.
Thank you to our community for waiting patiently and building alongside us.
#ModCon2026
Full blog: modular.com/blog/mojo-open-s…
47
226
1,414
96,412
Keynote starting in a few minutes! Let us know where you're joining from in the livestream chat:
piped.video/watch?v=Yvb_G2Dr…
#ModCon2026
1
6
33
2,346
ModCon 2026 is open! Badges are printing, coffee is hot, and the livestream kicks off at 9 AM. Join us virtually from anywhere to hear the big announcements!
piped.video/watch?v=Yvb_G2Dr…
#ModCon2026
2
27
2,439
Our biggest product announcements of the year land tomorrow in the ModCon 2026 opening keynote. 9:00 AM PT.
Chris Lattner, Tim Davis, Eric Johnson, and Mostafa Hagog deliver The Unified AI Compute Layer, alongside Cristiano Amon and Rashid Attar of @Qualcomm, Anush Elangovan of @AMD, and Darko Todorovic of @HTECgroup.
If you only watch one thing from ModCon, watch this.
Free livestream: luma.com/modcon-livestream
2
9
52
7,999
MiniMax designed H3 for hardware compatibility from the earliest stages, then opened the weights so people could run it across even more silicon.
Morgan Suo, Head of US Business Development at @MiniMax_AI, joins ModCon '26 to share what open-weight omni-context generation enables for AI video.
Aug 18, Grand Hyatt SF. Register for the livestream: luma.com/modcon-livestream
9
3
26
14,097
Building frontier models involves a hundred decisions rarely discussed publicly: when to stop scaling, what data to keep, how to differentiate, whether to release the weights.
On August 18th at ModCon '26, Paige Bailey of @GoogleDeepMind, Joseph Spisak of @reflection_ai, Victor Su-Ortiz of @MiniMax_AI, and Varun Randery of @poolsideai are talking through the challenges of the industry from four different vantage points.
Register for the livestream: luma.com/modcon-livestream
2
4
29
11,356
Most data centers were built on old assumptions: big training jobs, homogeneous fleets, and plenty of time to plan capacity. Inference broke all three.
At ModCon '26, Jay Jackson (SVP, @OracleCloud) and @jtatarchuk (Co-Founder & CGO, @tensorwave) join us for a fireside chat to weigh in on the future of the data center.
Catch the conversation via livestream: luma.com/modcon-livestream
3
15
2,029
.@_micah_h of @ArtificialAnlys and @dylan522p of @SemiAnalysis_ know more about the current state of AI compute than almost anyone. They're both joining our Analyst Perspectives fireside chat at ModCon on August 18th. Moderated by our own @iamtimdavis.
Register for the livestream or grab a spot on the in-person waitlist to hear their hot takes on where the industry is headed:
luma.com/modcon
luma.com/modcon-livestream
2
29
2,188
If you were starting from zero today, where would you invest your first dollar in AI infra? At ModCon 2026, we're asking five investors who already have full portfolios to answer anyway: @davemuni of @GVteam, @samofort of @DFJvc, Liz Stein of @USITfund, @quentinclark of @generalcatalyst, and @michhgonz of @Microsoft's @M12vc, moderated by @iamtimdavis.
Grab a ticket while supplies last: luma.com/modcon
1
5
21
4,384
Missed week 1? Catch the recording on our YouTube channel, and leave your questions in the comments: piped.video/watch?v=1Jqp0Bhe…
3
1,173
Session 1 of Mojo 101 streamed yesterday, and the turnout was great. Our live chat was full of insightful questions.
If you missed it (or want to rewatch), the recording of Language Fundamentals is up now on YouTube: piped.video/watch?v=1Jqp0Bhe…
1
14
2,562
ModCon '26 brings together the people setting the direction for AI infrastructure. Hear from @clattner_llvm, @Qualcomm's @cristianoamon, @GoogleDeepMind's @DynamicWebPaige, @SemiAnalysis_'s @dylan522p, and more.
Grab your ticket: modular.com/modcon?utm_sourc…
2
3
42
246,178
Modular is live on @ArtificialAnlys with 3x faster image generation than the competition.
MAX inference serving @bfl_ai’s FLUX.2-dev achieves state of the art latency per AA’s new benchmarking: artificialanalysis.ai/image/…
1
6
26
5,160
Two chances to learn about our stack today at @aiDotEngineer World's Fair in San Francisco:
#1. MAX in Action: Sub-Second FLUX.2 on Any GPU - 11-11:30 AM at our booth (U-G28) with @ConorBronsdon, Technical Ecosystem Lead
#2. Modular: Taming the AI Hardware Cambrian Explosion - 3:45-4:05 PM at Expo Stage 1 NE with Abdul Dakkak, Chief Scientist
Want to talk about optimizing your team's inference stack IRL this week? Book time with us: modular.com/aie-2026?utm_sou…
2
17
1,869
Mojo Quest launches today! Mojo Quest is a browser-based game for learning Mojo syntax by closing engineering tickets for a fictional robotics company.
quest.mojolang.org/
1
2
66
3,503
We had a blast at the official @aiDotEngineer hackathon with @cerebral_valley, @GoogleDeepMind, @MiniMax_AI, @digitalocean, @MongoDB, and @livekit. Thanks to everyone who came out and hacked with us!
We're at Booth UG28 all week at AI Engineer World's Fair. Want to see how Modular Platform could optimize your company's stack? Grab time with our team here: modular.com/aie-2026
1
2
54
3,970
ModCon is back.
August 18th. San Francisco.
A full day of AI infrastructure talks, launches, and workshops, with speakers including @dylan522p of @SemiAnalysis_ , @jerryjliu0 of @llama_index, @DynamicWebPaige of @GoogleDeepMind, and @sidsheth of @dMatrix_AI.
Limited spots. Early-bird pricing ends July 1st.
Get your ticket: modular.com/modcon?utm_sourc…
1
9
31
11,622
GLM 5.2 is built for long-horizon tasks - get all the benchmarks and learn more about the model in @Zai_org's great blog post: z.ai/blog/glm-5.2
6
731
.@zai_org open-sourced GLM 5.2 today, and Modular is a Day Zero launch partner.
GLM 5.2 is their new flagship for coding and long-horizon agentic work, with usable 1M-token context built for tasks that run long and call a lot of tools.
Serving a model like this well is a full-stack problem. As context grows, the KV cache grows with it, and doing it economically at high concurrency takes more than a config flag. The Modular stack optimizes the path from GPU kernels to serving, which lets us run frontier open models on Day 0 with the utilization and economics agent workloads need.
It's available on Modular Cloud now. Request access: console.modular.com/signup
2
5
55
3,336
.@iamtimdavis built a retro platformer where the terrain is generated by SIMD kernel computation.
Meet GPU Boost Adventure. A neon, CRT-flavored endless runner. boost.modular.com
2
6
43
3,357
M3 open weights from @MiniMax_AI just dropped, and Modular is a Day Zero launch partner.
1M-token context. Text, image, and video input. Built for long-running agent and coding workloads.
Read our full announcement: modular.com/blog/day-zero-mi…
2
7
49
11,881
Our kernel team has been deep in MiniMax M3 all week. The 1M-token context and native multimodality make it a hard model to serve well, which is exactly the kind of problem we like!
When the open weights drop in the next few days, you'll be able to run it on Modular right away.
Stay tuned for @MiniMax_AI x Modular.
5
6
127
23,718
Don't see your company? Drop your URL and watch it generate: inkwell.modular.com/founders…
If you're deploying image gen at scale, our team wants to hear what you're building: modular.com/request-demo
1
2
570
Working through our GPU Puzzles? Don't sleep on our companion YouTube series that walks through puzzles 1 through 5. Follow along, pause, and rewind to make sure you grok the solution: piped.video/watch?v=-VsP4kT6…
3
17
1,755
At @AMD AI DevDay, @clattner_llvm showed that AMD MI355X paired with Modular platform delivers equivalent image gen performance to Blackwell at 5.5x lower total cost.
Watch Chris' luminary talk: piped.video/watch?v=FjFC__Hx…
Thanks again to @AIatAMD for a great event!
1
2
21
2,492
In the latest Modular Tech Talk, Mojo Compiler Engineer Billy Zhu presents Mojo's attribute-based expression system and how it enables Mojo's powerful type-safe meta-programming:
piped.video/4DKInnobCjY
1
4
26
2,470
Seoul showed up! Packed room, sharp questions, a special message from @clattner_llvm, and an intro to Mojo 🔥 and MAX. Our first developer meetup in Korea. Thank you to SqueezeBits for making this happen, and to everyone who came out.
2
4
27
6,569
The MAX-LLM book just made it even easier to build an LLM from scratch.
The new notebook format lets you run the GPT-2 components interactively, inspect real tensor shapes, and generate text from pretrained weights.
Prefer to browse first? The pre-rendered version shows all outputs without running a cell:
github.com/modular/max-llm-b…
8
66
3,579
For engineers: hit the </> button in Inkwell and dev mode stays on across every page.
You'll see exactly how fast each image is generating in real time: latency, tokens/sec, and more. Powered by Modular Cloud.
Try it at inkwell.modular.com
6
520
Every Inkwell story stars a character you build. Pick the species, the hair, the outfit. Watch them come to life across an endless branching story, illustrated on every page.
Make yourself the hero at inkwell.modular.com. Tag us in what you create. We're sending swag to our favorites.
1
1
6
631
Our cofounder @iamtimdavis built an AI storybook app using @BlackForestLabs' FLUX2 and @googlegemma 4 on Modular Cloud. Pick a character, make choices, and the story branches endlessly, with every page written and illustrated in real time.
Tim has spent his career obsessing over inference latency, first at Google, now at Modular. Building something his kids use settled it: in a real-time generative app, the inference platform determines the experience as much as the model.
The numbers back that up. From 24 hours of production traffic: first prose in 420ms, a full illustration in under 6 seconds, 85% of page turns in 48ms.
Create your own story with Inkwell and share it. We're sending swag to our favorites: inkwell.modular.com/
2
7
40
15,274
"The people who see the most pain are the people writing at the low level and optimizing at the low level. So that's why we love Mojo and MAX - we think that's a way to compete on the same level playing field."
- Ramine Roane @roaner, CVP of AI at @AMD, at Full Context, our reception with AMD before their AI DevDay
This is the conversation we built these events for. Subscribe to our events calendar: luma.com/modular-ai
1
2
27
1,487
Nerdearla @nerdearla is the largest free tech event in the Spanish-speaking world. This year, @clattner_llvm talked about why the AI stack is broken and what we're doing to fix it with Mojo and MAX. Catch the recording on YouTube: piped.video/watch?v=Kw2FLI7L…
6
21
2,232
We're on the floor at @AMD AI DevDay! Stop by our booth to talk high-performance inference with AMD + Modular, and don't miss @clattner_llvm's luminary talk at 3:10 PM.
3
27
1,156
Two days left until @AMD's AI DevDay! Don't miss @clattner_llvm's luminary talk covering how we fused FLUX.2 into a single execution graph, with a 3.8x speedup torch.compile on MI355X, under 3.5s per image, sub-700MB container. Plus, 5.5x lower cost than running on competing hardware.
Stop by the Modular booth to connect with our team, learn about open roles, and score swag.
Grab your spot: amd.com/en/corporate/events/…
1
1
18
937
Missed today's community meeting? The recording is now on our YouTube channel: piped.video/watch?v=0gOGXHTQ…
Tune in to hear about Mojo support on Tensara and ffmpeg Mojo bindings. Built by the community, presented by the builders. Plus, catch Q&A at the end with the team.
1
2
16
2,414
Most serving stacks run FLUX.2 as four separate stages with Python overhead between each one. We collapsed all four into a single fused execution graph using MLIR-based compilation.
On @AMD MI355X, that means a 3.8x speedup over torch.compile, 1024x1024 images in under 3.5 seconds, and a deployment container under 700MB. We ran the same pipeline on Blackwell, too. AMD delivers equivalent generation quality at a 5.5x lower cost.
@clattner_llvm is presenting the full breakdown at AMD AI DevDay. Register: amd.com/en/corporate/events/…
2
13
53
6,318
We sat down with Kyle Caverly, an AI Performance Engineer on the MAX serve team, to walk through what actually happens inside an inference server from prompt to response.
All the code discussed is open source.
piped.video/hewZwTwDBcM
2
5
16
2,707
Our VP of Engineering Mostafa Hagog takes the stage at @TensorWave's Beyond Summit today at 2pm.
Come hear Mostafa talk Mojo 🔥, MAX, and heterogeneous compute: how they fit together as a platform for teams tired of rewriting the same inference stack every time the hardware changes.
Come find us if you're attending!
2
16
1,188