Posts tagged models

Showing posts about models

Browse by topic

5 posts in this topic

All posts (22)

ai (16)agents (12)memory (7)models (5)architecture (4)systems (4)trajectories (4)research (3)

Show 59 more topics

aimodelsdiffusion

DiffusionGemma: The Developer Guide

Google's experimental DiffusionGemma (26B MoE on the Gemma 4 backbone) replaces autoregressive token-by-token generation with diffusion-based parallel decoding on 256-token blocks, delivering up to 4x faster inference, bidirectional context, and built-in self-correction while remaining practical to serve and fine-tune.

Jun 11, 2026Read

aimodelsimage-generation

Bonsai Image 4B: Local Ternary Image Generation on an M4 Pro

A long-form tutorial for running PrismML's Bonsai Image 4B locally with the ternary MLX backend, higher-quality 4-step previews, source links, and honest M4 Pro measurements.

Jun 7, 2026Read

aiagentsmodels

Holo3.1 and Desktop Vision Agents

H Company’s Holo3.1-35B-A3B is less interesting as another model leaderboard entry than as a signal about local computer-use agents, UI grounding, and efficient active-parameter architectures.

Jun 6, 2026Read

aimodelsmultimodal

Gemma 4 12B Unified

Google's open-weight Gemma 4 12B-it folds text, image, and audio into a single model with no separate encoders, runs on a 16GB Mac after 4-bit quantization, and posts benchmarks well above its parameter count.

Jun 4, 2026Read

aimodelsresearch

HRM-Text-1B and Efficient Pretraining

Sapient's HRM-Text-1B is a useful signal: architecture and training objective can still move the efficiency frontier, not just model size.

May 21, 2026Read