Pokee-Isaac 28B: 10M-token context, deployable on a single GPU

Post Log inSign up Post Pokee AI @Pokee_AI Releasing Pokee-Isaac 28B — the world’s first real 10M-token context frontier-class agentic model, deployable on a single GPU (starting from RTX 4090 or equivalent). New proprietary non-decoder-only architecture: • 93.3% RULER at 10M tokens • Up to 137K tokens/s prefill on one B200 with 10M-token context • Leads BFCL v4 and τ³-bench in our evaluation • Lowest combined attack success rate among evaluated models on DTAP security red-teaming benchmark Pricing and deployment: 💰 $0.15/M input · $1/M output 🔒 Deploy in your VPC, on-premises, or on-device, with Day-0 support for @vllm_project and @sgl_project Technical blog: console.pokee.ai/model Technical report: console.pokee.ai/pokee-isaac-28… API: console.pokee.ai 4:46 PM · Aug 4, 20261.2MViews Pokee AI @Pokee_AI 20h Pokee-Isaac uses a proprietary non-decoder-only architecture. While some weights are fine-tuned from Qwen3.6-27B under Apache 2.0, Isaac is not a conventional Qwen fine-tune and other weights of Isaac are trained from scratch by Pokee AI team. Alexey Fateev @superalesha 22h HF Link? 🔗 GIF