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

Pokee-Isaac 28B, the world's first real 10M-token context frontier-class agentic model, is now deployable on a single GPU starting from RTX 4090, according to its release announcement. The model achieves 93.3% RULER at 10M tokens, up to 137K tokens/s prefill on one B200, and leads BFCL v4 and τ³-bench evaluations, with pricing at $0.15/M input and $1/M output.

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