Weekly archive

New local AI models, Mar 16–22, 2026

3 open models released Mar 16–22, 2026, with how each runs on five reference devices.

  1. Nemotron Cascade 2 30B-A3B

    NVIDIA · LLM · 32B (3.5B active) ·

    80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

    Memory, every quant and how to run it Check your own device

  2. Qianfan-OCR 4B

    Baidu · LLM · 4.7B ·

    50Fair quality (C) · 50 of 100: how capable the model is at F16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

    Memory, every quant and how to run it Check your own device

  3. Chandra OCR 2

    Datalab · LLM · 5.3B ·

    48Fair quality (C) · 48 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

    Memory, every quant and how to run it Check your own device

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.

Was this page helpful?