RC RANDOM CHAOS

edge AI

2 posts

MicroLLM Lab runs seven models without touching the network
Article

MicroLLM Lab runs seven models without touching the network

MicroLLM Lab runs seven 25M-360M parameter language models in the browser via WebGPU, on-device with no server, and benchmarks their speed and accuracy.

 One billion fire, eight billion sit in memory
Article

One billion fire, eight billion sit in memory

Liquid AI's LFM2.5-8B-A1B is an 8B edge MoE firing ~1B active params per token, with 128K context, reasoning-only output, and fast CPU and GPU inference.