Weekly archive

New local AI models, Dec 15–21, 2025

3 open models released Dec 15–21, 2025, with how each runs on five reference devices.

  1. MiniMax M2.1 (230B-A10B)

    MiniMax · LLM · 229B (10.0B active) ·

    90Excellent quality (A+) · 90 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  2. MiMo V2 Flash (309B-A15B)

    Xiaomi · LLM · 310B (15.0B active) ·

    88Excellent quality (A+) · 88 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  3. Qwen-Image-Edit 2511

    Alibaba · Image · 20.4B ·

    86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 69/100 (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?