Weekly archive

New local AI models, Sep 9–15, 2024

4 open models released Sep 9–15, 2024, with how each runs on five reference devices.

  1. Flow Judge v0.1

    Flow AI · Decision · 3.8B ·

    63Good quality (B) · 63 of 100: how capable the model is at Q6_K, 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

  2. Solar Pro Preview 22B

    Upstage · LLM · 22B ·

    57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  3. Pixtral 12B (2409)

    Mistral AI · LLM · 12B ·

    49Fair quality (C) · 49 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  4. Nemotron Mini 4B Instruct

    NVIDIA · LLM · 4.2B ·

    22Basic quality (D) · 22 of 100: how capable the model is at F16, whatever it runs on. Match score 52/100 (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?