Modal @modal

AI infrastructure that developers love 💚 Run inference, sandboxes, batch processing, training, and many other things on Modal modal.com New York City Joined July 2022

Tweets

2K
Followers

40K
Following

166
Likes

4K

Daniel Shaar @dshaar_

21 hours ago

x.com/i/article/2112…

5 15 91 19K 60

View Details

Voice agents, multiplayer games, and other workloads need to maintain continuity between requests. With Sticky Sessions, built on Modal's serverless Servers, you can route requests in a session to the same container and autoscale with demand. Here's a look at how we built it:

Daniel Shaar @dshaar_

21 hours ago

x.com/i/article/2112…

5 15 91 19K 60

5 2 45 3K 13

View Details

Modal @modal

a day ago

Congrats to @GradiumAI on launching Phonon! We built a voice agent with their new TTS models and Pipecat on Modal to put them to work. Read more about Phonon and check out the demo: gradium.ai/phonon

Gradium @GradiumAI

a day ago

A new frontier for on-device speech. We're open-sourcing Phonon, a suite of TTS models under 50m parameters, setting a new standard for naturalness and accuracy across languages, with the broadest inference support to date. Phonon-31m is available under Apache 2.0.

147 265 2K 295K 2K

2 5 40 2K 7

View Details

Charles 🎉 Frye @charles_irl

2 days ago

@modal and @GrayAreaorg are partnering to put the "art" back in "artificial intelligence". We've sponsored a dozen projects by leading digital artists that will be shown at Gray Area next week. Come thru on Thursday for a panel featuring @ideeplistening and @Ryphi10. Register here: luma.com/modal-48ev

1 8 36 3K 12

View Details

Modal @modal

2 days ago

More than 40x the parameters of Mercury 1, still running at 1,000+ tokens/sec. Congrats to the @_inception_ai team on Mercury 3!

Stefano Ermon @StefanoErmon

2 days ago

1/4 Today, we’re releasing Mercury 3. Mercury 3 is by far our most powerful model and the most intelligent diffusion LLM ever released. It outperforms GPT-6 Luna and Haiku 5.5 on quality while running at 1000+ tok/sec.

285 452 5K 455K 2K

6 6 136 8K 20

View Details

Modal @modal

2 days ago

Read about how we benchmarked Vera, what we found, and why we're excited about its potential for Sandboxes: modal.com/blog/nvidia-ve…

2 1 11 1K 2

View Details

Modal @modal

2 days ago

We got our hands on @nvidia's new Vera CPU and put it to the test. We built a benchmark using real-world agentic workloads to see how it performs under contention. In early tests, Vera delivered up to 2x the throughput of comparable x86 hardware, maintaining low latency even as hundreds of concurrent workloads competed for resources. For Modal Sandboxes, that could mean running more agents in parallel without sacrificing latency.

29 27 225 27K 36

View Details

Modal @modal

5 days ago

When we introduced VM Sandboxes, we wanted to preserve Modal’s sub-second cold starts without compromising performance. We ended up building a new filesystem stack that dramatically improved performance, and wrote about the engineering challenges and decisions that got us there.

Amit @amitpr

5 days ago

The secret to Modal's speed is our custom lazily loaded container filesystem, ImageFS. ImageFS is built on a massive tiered distributed filesystem, layering local NVMe disks, regional and p2p caches, and global blob stores. When we launched VM Sandboxes this month, we wanted to

13 30 543 52K 402

5 9 143 8K 58

View Details

Modal @modal

5 days ago

@ericyuegu @ajhinh 💚🚀

0 0 1 51 0

View Details

Eric Gu @ericyuegu

5 days ago

1/ I trained an AI to be top 1% in the world at Super Smash Bros. Melee by watching 80k hours of human replay. Meet HAL.

148 120 2K 370K 654

View Details

Modal @modal

5 days ago

Learn more and deploy Reflection Beam as a Dedicated Endpoint on Modal: modal.com/library/reflec…

0 0 4 697 0

View Details

Modal @modal

5 days ago

Reflection Beam is now available on Modal. Beam is a 501B-parameter open-weight MoE (23B active) from @reflection_ai built for coding, agentic workflows, and reasoning. It supports a 1M token context window, with token efficiency a core focus. In early access, the Oura Health Intelligence team found that "Beam had fewer context leaks and was much more grounded in its answers than other frontier models we evaluated.”

3 8 82 4K 10

View Details

kwindla @kwindla

6 days ago

Fast is better than slow. We've got two new PhoneLLM models optimized for conversational voice AI. PhoneLLM Mini (30B) — When you need the lowest possible latency (sub-100ms TTFAT), smallest model size, and lowest cost. Good multi-turn conversation behavior and tool-calling accuracy in a model that can run >100 concurrent agents on a B200 and fits on an RTX 5090. PhoneLLM Max (120B) — A "microthinking" model for complex conversational tasks. Sub-200ms TTFAT. SOTA task completion performance at 1/10th the latency and cost of models with similar capabilities. Both of these models are full-weights fine-tunes of @NVIDIAAI Nemotron models. Mini is based on Nemotron 3 Nano. Max is based on the brand new Nemotron 3.5 Super VL. Both of these models are available as open weights on HuggingFace, and from four inference partners: AWS, Baseten, Cloudflare, and Modal.

25 35 201 12K 152

View Details

Modal @modal

6 days ago

Learn more and deploy Nemotron 3.5 Super VL as a Dedicated Endpoint on Modal: modal.com/library/nvidia…

0 0 3 384 0

View Details

Modal @modal

6 days ago

Watch the full talk: youtu.be/qVIndplKC6Q

1 0 2 1K 0

View Details

Modal @modal

6 days ago

Nemotron 3.5 Super VL from @nvidia is live on Modal today with 120B params for visual reasoning and agentic work across images, docs, and UIs. Hear more about the thinking behind the Nemotron family: At Runtime, @ctnzr explained why “efficiency is also intelligence,” and how NVIDIA pre-trained Nemotron 3 Ultra entirely in FP4.

1 11 36 3K 4

View Details

Modal @modal

6 days ago

Deploy Muse Spark Open as a Shared Endpoint with per-token billing on Modal. Read the blog for more details: modal.com/blog/meta-muse…

0 0 2 653 0

View Details

Modal @modal

6 days ago

Muse Spark Open, a coding-optimized open weight model from @Meta, is now available on Modal. Muse Spark Open is the most capable US open weight model to date and is trained specifically for agentic coding and long-horizon tasks; it supports native multimodal understanding and supports a 1M token context window.

4 6 67 4K 4

View Details

Modal @modal

6 days ago

Learn more and deploy Nemotron 3.5 Super VL as a Dedicated Endpoint on Modal: modal.com/library/nvidia…

0 0 0 538 0

View Details

Modal @modal

6 days ago

Nemotron 3.5 Super VL from @nvidia is now available on Modal. With 120B total parameters and 12B active per token, this open-weight multimodal model brings powerful visual reasoning to documents, images, and application screenshots—enabling sophisticated agentic workflows.