Weekly archive

New local AI models, Nov 2–8, 2026

2 open models released Nov 2–8, 2026, with how each runs on five reference devices.

  1. Kimi K3.1 Pro (2.8T)

    Moonshot AI · LLM · 2,780B (104.0B active) ·

    69Good quality (B) · 69 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.
    New

    Runs on

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

  2. S5 nano

    Maritaca AI · LLM · 4.7B ·

    37Basic quality (D) · 37 of 100: how capable the model is at F16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.
    New

    Runs on

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

Being checked 4 more models

Found on Hugging Face and not in the catalog yet. Image, video and decision models need measured timings, and some language models do not state every figure the calculator needs, so these are checked by hand. The ones that pass get a page and grades with the weekly review; until then each link goes to the model's own Hugging Face page.

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?