Weekly archive

New local AI models, Jan 27 – Feb 2, 2025

4 open models released Jan 27 – Feb 2, 2025, with how each runs on five reference devices.

  1. Qwen2.5-VL 72B Instruct

    Alibaba · LLM · 73B ·

    69Good quality (B) · 69 of 100: how capable the model is at Q4_K_M, 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

  2. Mistral Small 3 24B (2501)

    Mistral AI · LLM · 24B ·

    60Good quality (B) · 60 of 100: how capable the model is at Q4_K_M, 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

  3. DeepScaleR 1.5B Preview

    Agentica · LLM · 1.8B ·

    26Basic quality (D) · 26 of 100: how capable the model is at F16, 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

  4. OLMoE 1B-7B Instruct

    Ai2 · LLM · 6.9B (1.3B active) ·

    26Basic quality (D) · 26 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

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?