Mount Thor (@themountthor) header
Mount Thor (@themountthor) profile picture

Cloud Infrastructure for Apple Hardware

Joined March 2026
Mount Thor retweeted
Your agents can finally use a Mac. macOS Sandboxes are now live on @daytonaio: M4, M4 Pro and M5 Pro. Spin one up at app.daytona.com
133
62
64
924
219,009
Mount Thor retweeted
Many companies own a fleet of devices capable of running AI locally, but have no means of combining them into one AI server. Today we're releasing our technical paper on Superfluid, which does exactly that. We get fleet throughput of over 10,650 tok/s on 12x Mac Studio's M3 Ultra for 384 concurrent agents (Qwen 3.6-35B). We also benchmark Superfluid on heterogeneous local AI clusters combining Apple, AMD and NVIDIA devices. Superfluid is open source and supports llama.cpp, MLX and BaseRT: github.com/basecompute/super… A huge thanks to @petervoell and the team at @themountthor for early access to their Apple silicon cluster that allowed us to evaluate Superfluid at scale.
2
4
2
12
8,185
in case this wasn't already obvious there's a very fine line between this and @petervoell apologies in advance / retrospect
3
1,062
Mount Thor retweeted
Apple silicon is quietly becoming real AI infra. Agents need Macs. Computer-use RL, macOS sandboxes, long-running agents and cheaper open-model inference on M-series. I co-led Mount Thor’s first two rounds because nobody was running this at datacenter scale and @petervoell was the right founder to take this on. Six months since founding, we're live with many customers across multiple sites. If you need Apple silicon at scale for AI workloads, DM me. Happy to intro.
Agentic AI runs best on Apple platforms. Accessing Apple’s hardware at scale has been hard, until now. We’re making macOS and Apple silicon available as elastic compute resources, optimized for AI research & deployment.  We have one of the largest fleets in the world, support the most demanding workloads (massive 512GB M5 Ultra clusters, anyone?), and we’re just getting started. Wouldn’t be here without @CRV (@brittwalker_), @conviction (@pranavreddy), @chadbyers, @offlineventures (@davemorin), and others (including many inside @Apple) who believed in us early and remain incredible partners. We seek infinite games; the play continues. blog.mountthor.com/a
5
6
75
5,298
Agentic AI runs best on Apple platforms. Accessing Apple’s hardware at scale has been hard, until now. We’re making macOS and Apple silicon available as elastic compute resources, optimized for AI research & deployment.  We have one of the largest fleets in the world, support the most demanding workloads (massive 512GB M5 Ultra clusters, anyone?), and we’re just getting started. Wouldn’t be here without @CRV (@brittwalker_), @conviction (@pranavreddy), @chadbyers, @offlineventures (@davemorin), and others (including many inside @Apple) who believed in us early and remain incredible partners. We seek infinite games; the play continues. blog.mountthor.com/a
13
17
16
201
1,288,858