Releasing Pokee-Isaac 28B โ the worldโs 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:
โข 93.3% RULER at 10M tokens
โข Up to 137K tokens/s prefill on one B200 with 10M-token context
โข Leads BFCL v4 and ฯยณ-bench in our evaluation
โข Lowest combined attack success rate among evaluated models on DTAP security red-teaming benchmark
Pricing and deployment:
๐ฐ $0.15/M input ยท $1/M output
๐ Deploy in your VPC, on-premises, or on-device, with Day-0 support for @vllm_project and @sgl_project
Technical blog: https://t.co/nFqaYBlcQP
Technical report: https://t.co/XDOoZxpgJx
API: https://t.co/KYj8fOOjNS
Today we release LFM2.5-2.6B, an agentic model that runs entirely on-device. It plans, calls tools, and works through multi-step tasks on phones, laptops, PCs, and robots. Data never leaves the device, and the marginal cost of each run is essentially zero.
> Pre-trained on ~34T tokens
> LFM2.5 flagship hybrid architecture
> Context length: 128K
> Vocab size: 128K
> balanced intelligence per watt
> customizable on a single GPU for any specialized task
> LFM2 open-weight license
Comparable or better scores compared to models up to nearly 4x its size:
> ToolSandbox 77.83, ahead of Qwen3.5-9B at 76.44
> Multi-IF 80.07, ahead of Gemma-4-E4B-it at 77.35
> IFStruct 85.49, ahead of Qwen3.5-9B at 78.50
๐งต