Weekly archive

New local AI models, Jul 28 – Aug 3, 2025

10 open models released Jul 28 – Aug 3, 2025, with how each runs on five reference devices.

  1. Qwen-Image

    Alibaba · Image · 20.4B ·

    88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, 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

  2. Qwen3 30B-A3B Thinking 2507

    Alibaba · LLM · 31B (3.3B active) ·

    78Great quality (A) · 78 of 100: how capable the model is at F16, 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

  3. Qwen3 Coder 30B-A3B

    Alibaba · LLM · 31B (3.3B active) ·

    78Great quality (A) · 78 of 100: how capable the model is at F16, 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

  4. Qwen3 30B-A3B Instruct 2507

    Alibaba · LLM · 31B (3.3B active) ·

    77Great quality (A) · 77 of 100: how capable the model is at F16, 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. Hunyuan 7B Instruct

    Tencent · LLM · 7.5B ·

    52Fair quality (C) · 52 of 100: how capable the model is at Q8_0, 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. Hunyuan 4B Instruct

    Tencent · LLM · 4.2B ·

    42Fair quality (C) · 42 of 100: how capable the model is at F16, 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

  7. AFM 4.5B

    Arcee AI · LLM · 4.6B ·

    40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  8. Hunyuan 1.8B Instruct

    Tencent · LLM · 1.8B ·

    22Basic quality (D) · 22 of 100: how capable the model is at F16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  9. Hunyuan 0.5B Instruct

    Tencent · LLM · 0.5B ·

    8Basic quality (D) · 8 of 100: how capable the model is at F16, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  10. Gemma 3 270M

    Google · LLM · 0.3B ·

    6Basic quality (D) · 6 of 100: how capable the model is at F16, whatever it runs on. Match score 44/100 (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?