AI & ML interests

Bit-exact lossless model compression

Recent Activity

kunleolutomilayo  updated a Space 9 days ago
isiroai/README
kunleolutomilayo  updated a model 26 days ago
isiroai/Qwen3.8-27B-TIC
kunleolutomilayo  published a model 26 days ago
isiroai/Qwen3.8-27B-TIC
View all activity

Organization Card

ISIRO Runtime

Lossless inference layer for self-managed AI

Smaller weights · More KV cache · No quantization

Baseline model weights compressed to .tic with bit-exact decode via ISIRO Runtime

ISIRO compresses AI model weights losslessly.
Weights are bit-exact, with a hash manifest for verification, and are served directly in the compressed state.
No quantization, no retraining, no model changes.

Lower cost to self-manage models in cloud and on-prem.

Download sample .tic models or compile your own with ISIRO compiler.
What is TIC?

Install: curl -fsSL https://isiro.ai/install.sh | sh

Documentation · GitHub · isiro.ai

datasets 0

None public yet