Weekly archive

New local AI models, Jun 22–28, 2026

3 open models released Jun 22–28, 2026, with how each runs on five reference devices.

  1. Agents-A1 35B-A3B

    InternScience · LLM · 35B (3.0B active) ·

    87Excellent quality (A+) · 87 of 100: how capable the model is at F16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  2. Qwen AgentWorld 35B-A3B

    Alibaba · LLM · 35B (3.0B active) ·

    87Excellent quality (A+) · 87 of 100: how capable the model is at F16, whatever it runs on. Match score 85/100 (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 230M

    Liquid AI · LLM · 0.2B ·

    10Basic quality (D) · 10 of 100: how capable the model is at F16, whatever it runs on. Match score 46/100 (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?