Long-horizon agents accumulate context faster than they resolve tasks. Every tool output, observation, and intermediate reasoning step remains in the window, and the two capabilities that matter—holding that context and staying coherent across it—have so far been available almost exclusively from cloud endpoints. That limitation excludes regulated industries, public-sector institutions, and on-device applications where data is not permitted to leave the boundary at all. Pokee AI has released Pokee-Isaac 28B, a 28B text-only foundation model with a 10M-token context window, designed to operate entirely within the customer boundary. The Pokee research team reports 93.3% on RULER at 10M tokens, parity with the strongest cost-optimized cloud baselines on agentic benchmarks, and a serving profile that fits on a single GPU.
Deployability
Yes—but licensed, not open-weight. Pokee AI serves Isaac through an OpenAI-compatible developer API and licenses it for deployment inside a VPC, on-premises, or on-device. The launch announcement advertises Day-0 support for vLLM and SGLang, with single-GPU serving starting from an RTX 4090 or equivalent. However, the research team publishes measurements only from a single B200-class GPU, so treat the consumer-GPU claim as vendor guidance rather than a reported result.
Company Level
This model suits organizations that already own their inference stack—mid-size and enterprise teams with a platform group, plus device OEMs. A solo practitioner without on-prem hardware should use the hosted API instead; the boundary argument only pays off if you have a boundary.
Industries
Healthcare and payors, financial services and insurance, defense and public sector, legal and e-discovery, and pharma or semiconductor R&D. The common trait is a rule that data cannot cross an external API boundary, not merely a preference for privacy.
Applications
Whole-repository code review, multi-year contract and claims analysis, and other long-horizon tasks that require sustained reasoning over vast datasets without external transmission.
via MarkTechPost