next-gen ai platform
the fintech os for ai
powered by our breakthrough tapsilat-o1 model, built for zero-latency financial intelligence.
user@tapsilat-os:~
$ tapsilat --serve --model=tapsilat-o1
starting tapsilat cli...
loading tapsilat-o1 (4b params, 4-bit)... [done]
model architecture
a highly optimized mixture of experts (moe) architecture featuring 4b parameters with 4-bit quantization for zero-latency execution.
advanced capabilities
native support for deep thinking and function calling, seamlessly integrated with evaluation harness frameworks.
system requirements
designed for extreme efficiency. requires only 8gb of unified memory to run full-context inference entirely locally, no internet required.