Weekly archive

New local AI models, Aug 4–10, 2025

9 open models released Aug 4–10, 2025, with how each runs on five reference devices.

  1. gpt-oss 120B

    OpenAI · LLM · 117B (5.1B active) ·

    84Great quality (A) · 84 of 100: how capable the model is at MXFP4, 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-4.5V

    Zhipu AI · LLM · 108B (12.0B active) ·

    79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  3. Hermes 4 405B

    Nous Research · LLM · 406B ·

    56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  4. Chroma1-HD

    Lodestone Rock · Image · 8.9B ·

    78Great quality (A) · 78 of 100: how capable the model is at FP16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  5. Baichuan M2 32B

    Baichuan · LLM · 33B ·

    66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, 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

  6. gpt-oss 20B

    OpenAI · LLM · 21B (3.6B active) ·

    70Great quality (A) · 70 of 100: how capable the model is at F16, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  7. Granite Embedding Reranker English R2

    IBM · Decision · 150M ·

    68Good quality (B) · 68 of 100: how capable the model is at F16, 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

  8. Qwen3 4B Thinking 2507

    Alibaba · LLM · 4.0B ·

    56Good quality (B) · 56 of 100: how capable the model is at F16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  9. Qwen3 4B Instruct 2507

    Alibaba · LLM · 4.0B ·

    54Fair quality (C) · 54 of 100: how capable the model is at F16, whatever it runs on. Match score 66/100 (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?