Weekly archive

New local AI models, Aug 24–30, 2026

5 open models released Aug 24–30, 2026, with how each runs on five reference devices.

  1. GLM-5.3 (753B-A40B)

    Zhipu AI · LLM · 753B (40.0B active) ·

    68Good quality (B) · 68 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  2. GLM-5.3 Flash (320B-A18B)

    Zhipu AI · LLM · 321B (18.0B active) ·

    92Excellent quality (A+) · 92 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  3. Qwen3.8 Flash Next (125B-A6B)

    Alibaba · LLM · 180B (6.0B active) ·

    96Excellent quality (A+) · 96 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  4. Hunyuan Hy4 Preview (780B)

    Tencent · LLM · 780B (55.0B active) ·

    67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  5. UI-Venus 2 9B

    Ant Group (inclusionAI) · LLM · 9.4B ·

    70Great quality (A) · 70 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 73/100 (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?