Weekly archive

New local AI models, Sep 2–8, 2024

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

  1. DeepSeek Coder V2 (236B)

    DeepSeek · LLM · 236B (21.0B active) ·

    70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  2. DeepSeek V2.5

    DeepSeek · LLM · 236B (21.0B active) ·

    66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  3. MiniCPM3 4B

    OpenBMB · LLM · 4.1B ·

    38Basic quality (D) · 38 of 100: how capable the model is at F16, whatever it runs on. Match score 59/100 (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?