Weekly archive

New local AI models, Sep 7–13, 2026

4 open models released Sep 7–13, 2026, with how each runs on five reference devices.

  1. DeepSeek V4.1 Flash (552B-A16B)

    DeepSeek · LLM · 763B (16.0B active) ·

    67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  2. Intern-S2 (397B-A17B)

    Shanghai AI Lab · LLM · 403B (17.0B active) ·

    92Excellent quality (A+) · 92 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  3. Kandinsky 6.0 Pro (29B, video + audio)

    Sber AI · Video · 30.1B ·

    88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  4. Kandinsky 6.0 Video Lite (3B, video + audio)

    Sber AI · Video · 3.2B ·

    68Good quality (B) · 68 of 100: how capable the model is at FP16, 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?