Weekly archive

New local AI models, Dec 2–8, 2024

4 open models released Dec 2–8, 2024, with how each runs on five reference devices.

  1. Granite 3.1 8B Instruct

    IBM · LLM · 8.2B ·

    44Fair quality (C) · 44 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  2. Hermes 3 Llama 3.2 3B

    Nous Research · LLM · 3.2B ·

    32Basic quality (D) · 32 of 100: how capable the model is at F16, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  3. Granite 3.1 2B Instruct

    IBM · LLM · 2.5B ·

    28Basic quality (D) · 28 of 100: how capable the model is at F16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  4. Granite 3.1 3B-A800M Instruct

    IBM · LLM · 3.3B (0.8B active) ·

    20Basic quality (D) · 20 of 100: how capable the model is at F16, whatever it runs on. Match score 51/100 (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?