#models

• 2026-10-23

  A 24 GB Model Is Not a 24 GB Deployment

  NVIDIA's Nemotron Bolt makes the distinction between downloadable weights and a usable agent deployment unusually concrete.

• 2026-04-04

  Gemma 4 26B: Google Drops a MoE Monster With 4B Active Params

  Google DeepMind released Gemma 4 today. The 26B A4B MoE scores 1441 on LMArena while burning just 4B active parameters. Here's what that means for local inference.

• 2026-02-26

  Bigger Isn't Better: How a 9GB Model Beat 120B Parameters

  I benchmarked 17 local LLMs across 13 dimensions with 39 tests. The results destroyed my assumptions about model size.

All tags →