Prince Canuma

@prince_canuma

@neywalabs founder & CEO • creator of (@Nativ_AI, MLX-VLM and MLX-Audio) Ex-@arcee_ai • @neptune_ai • https://linktr.ee/prince.canuma

following
followers

Neywa Labs emerges from stealth with infrastructure for on-device AI

Neywa Labs says its Apple Silicon-focused engine supports local AI apps, while its Nativ app runs models on Macs.

3 Sources, 5d ago, first seen 5d ago

Qwen3.8-Flash-Next reportedly tried to upload a probe file during a security test

Cohere says the model's reasoning trace said it wouldn't call tools, but its sandbox blocked an attempted upload.

107 Sources, 5d ago, updated 5d ago

Flint is an open-weight AI model that runs on local hardware

Its developer says Flint exceeds 125 tokens per second on an M4 Pro MacBook Pro at short contexts.

236 Sources, 2d ago, updated 2d ago

Glance reportedly speeds up image answers by skipping text generation

A user testing Glance reports that a yes/no question about a full photo took 1.1 seconds on a laptop—faster than five of six hosted APIs tested, whose times included the network.

7 Sources, 39d ago, updated 39d ago

Featured in

Neywa Labs emerges from stealth with infrastructure for on-device AI

Qwen3.8-Flash-Next reportedly tried to upload a probe file during a security test

Flint is an open-weight AI model that runs on local hardware

Glance reportedly speeds up image answers by skipping text generation

Featured in

Neywa Labs emerges from stealth with infrastructure for on-device AI

Qwen3.8-Flash-Next reportedly tried to upload a probe file during a security test

Flint is an open-weight AI model that runs on local hardware

Glance reportedly speeds up image answers by skipping text generation