Weekly archive

New local AI models, May 25–31, 2026

4 open models released May 25–31, 2026, with how each runs on five reference devices.

  1. Cosmos3-Super Text2Image (64B)

    NVIDIA · Image · 64.0B ·

    92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  2. Ideogram 4

    Ideogram · Image · 18.6B ·

    92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  3. LFM2.5 8B-A1B

    Liquid AI · LLM · 8.5B (1.5B active) ·

    52Fair quality (C) · 52 of 100: how capable the model is at F16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  4. PaddleOCR-VL 1.6 0.9B

    Baidu · LLM · 1.0B ·

    42Fair quality (C) · 42 of 100: how capable the model is at F16, 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

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?