Updated daily

New local AI models this week

3 open models released Nov 9–15, 2026, checked against phones, laptops, gaming PCs, edge boards and workstations. New open models are found on Hugging Face every day. Most language models are added to the whole site the same day; image, video and decision models, and language models whose files leave out a figure the calculator needs, are checked by hand and added with the weekly review.

  1. LongCat 2.5 (1.6T-A48B)

    Meituan · LLM · 1,780B (48.0B active) ·

    68Good quality (B) · 68 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. Nex N2.6 (321B-A18B)

    Nex-AGI · LLM · 321B (18.0B active) ·

    92Excellent quality (A+) · 92 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking.
    New

    Runs on

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

  3. MiniMax H3 Image

    MiniMax · Image · 33.1B ·

    91Excellent quality (A+) · 91 of 100: how capable the model is at FP8, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.
    New

    Runs on

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

Last week Nov 2–8, 2026 · 2 models

  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

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?