WebGuard CoreCybersecurity and threat intelligence releases

Press Release · Saturn Cloud

Saturn Cloud Brings Tileward's Compressed Models to Its Token Factory, Turning the Same GPUs Into More Tokens

Distributed by WebGuard Core · Originally issued via PR Newswire

Tileward's compressed open models free up GPU memory, so operators on Saturn Cloud's token factory platform can serve more tokens from the GPUs they already own, with no change to their serving stack or rate cards.

NEW YORK, Nov. 20, 2026 — Saturn Cloud, the inference platform for enterprises running open models, today announced a partnership with Tileward to bring its compressed open models to Saturn Cloud's token factory platform. Operators can run the same models with less GPU memory, so each GPU can serve more tokens.

Saturn Cloud's token factory turns GPU fleets into managed inference and fine-tuning services that operators sell to their own customers, under their own brand. Tenant isolation, quotas, metering, and enterprise governance are built in. It runs on NVIDIA Dynamo, in public cloud, private cloud, or on-premises. Serving Kimi K3 to 16 live agent sessions on NVIDIA GB300 GPUs, Saturn Cloud delivered 7,380 total tokens per second per GPU at about 37 tokens per second per user, matching the SemiAnalysis InferenceX benchmark recipe on the same GPUs. Tileward's models run on this serving stack.

"Operators sell inference from GPUs they've already paid for, and memory is usually what runs out first," said Sebastian Metti, Founder and CEO of Saturn Cloud. "Tileward gives that memory back, so operators can take on more customers and longer contexts with the fleet they have, without buying more GPUs."

Tileward, a member of the NVIDIA Inception program for startups, offers compressed models that are up to 78% smaller than the published weights. Tileward evaluates each one against the original on benchmarks including MMLU, SWE-bench Verified, and AgentBench.

"Making a model smaller was never the hard part. Proving it still gives the right answers is," said Anantha Sharma, Founder and CTO of Tileward. "We publish how we measure every model, so operators on Saturn Cloud can check the quality before they sell a single token of it."

Operators can swap in Tileward's weights for the published ones, and their serving stack, tenants, rate cards, and brand stay the same. The freed memory lets them run more copies of each model, fit large models on fewer GPUs, and serve more concurrent users with longer contexts. Serving more tokens from each GPU lowers the cost per token, giving operators more margin on input, cached, and output rates, or room to price lower.

Available Now on Saturn Cloud

Compressed versions of gpt-oss-120b, GLM-5.3, and DeepSeek-V4-Flash are available now to neoclouds, AI factory operators, telcos, sovereign AI providers, and enterprises running Saturn Cloud's token factory platform on their own GPUs. Contact Saturn Cloud or Tileward to add them to a deployment.

SOURCE Saturn Cloud

About Saturn Cloud

Saturn Cloud is the enterprise inference platform for open models and agents. Built on the NVIDIA inference stack, Saturn Cloud tunes each deployment to the customer's workload and optimizes throughput and latency to meet the contractual SLA. Enterprises run any open model or open-source agent on dedicated GPUs from Saturn Cloud's neocloud partners or inside their own networks, including air-gapped networks. GPU cloud operators use Saturn Cloud's token factory platform to sell inference from their own fleets. Learn more at saturncloud.io. 

About Tileward

Tileward makes open models smaller while preserving publisher accuracy and runs them as a hosted API, in a company's own cloud, or fully air-gapped. Learn more at tileward.com.