Weekly archive

New local AI models, Feb 24 – Mar 2, 2025

10 open models released Feb 24 – Mar 2, 2025, with how each runs on five reference devices.

  1. Wan 2.1 I2V 14B 720P

    Alibaba · Video · 14.0B ·

    78Great quality (A) · 78 of 100: how capable the model is at FP16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  2. Wan 2.1 T2V 14B

    Alibaba · Video · 14.0B ·

    78Great quality (A) · 78 of 100: how capable the model is at FP16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  3. Wan 2.1 I2V 14B 480P

    Alibaba · Video · 14.0B ·

    74Great quality (A) · 74 of 100: how capable the model is at FP16, 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. Gemma 3 27B IT

    Google · LLM · 27B ·

    68Good quality (B) · 68 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  5. Aya Vision 32B

    Cohere · LLM · 33B ·

    57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  6. Gemma 3 12B IT

    Google · LLM · 12B ·

    59Good quality (B) · 59 of 100: how capable the model is at Q6_K, 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

  7. Wan 2.1 T2V 1.3B

    Alibaba · Video · 1.3B ·

    55Good quality (B) · 55 of 100: how capable the model is at FP16, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  8. Aya Vision 8B

    Cohere · LLM · 8.6B ·

    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

  9. Phi-4 Multimodal Instruct

    Microsoft · LLM · 5.6B ·

    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

  10. Command R7B Arabic

    Cohere · LLM · 8.0B ·

    42Fair quality (C) · 42 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 61/100 (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?