Weekly archive

New local AI models, Apr 24–30, 2023

2 open models released Apr 24–30, 2023, with how each runs on five reference devices.

  1. StarCoder 15B

    BigCode · LLM · 16B ·

    25Basic quality (D) · 25 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  2. Falcon 7B Instruct

    TII · LLM · 7.2B ·

    6Basic quality (D) · 6 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 45/100 (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?