Weekly archive

New local AI models, Sep 28 – Oct 4, 2026

3 open models released Sep 28 – Oct 4, 2026, with how each runs on five reference devices.

  1. Mistral Large 4 (1T-A52B)

    Mistral AI · LLM · 1,053B (52.0B active) ·

    67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  2. Kolibri 1 (78B-A3.5B)

    Aleph Alpha · LLM · 78B (3.5B active) ·

    91Excellent quality (A+) · 91 of 100: how capable the model is at F16, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  3. FRIDA-Decisions

    Sber AI · Decision · 820M ·

    80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (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?