Weekly archive

New local AI models, Aug 25–31, 2025

6 open models released Aug 25–31, 2025, with how each runs on five reference devices.

  1. LongCat Flash Chat (560B)

    Meituan · LLM · 562B (27.0B active) ·

    83Great quality (A) · 83 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  2. InternVL3.5 241B-A28B

    Shanghai AI Lab · LLM · 241B (28.0B active) ·

    81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  3. InternVL3.5 38B

    Shanghai AI Lab · LLM · 38B ·

    72Great quality (A) · 72 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

  4. Wan 2.2 S2V 14B (speech to video)

    Alibaba · Video · 16.3B ·

    76Great quality (A) · 76 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

  5. Hermes 4 14B

    Nous Research · LLM · 15B ·

    65Good quality (B) · 65 of 100: how capable the model is at Q6_K, 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

  6. InternVL3.5 8B

    Shanghai AI Lab · LLM · 8.5B ·

    62Good quality (B) · 62 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (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?