Weekly archive

New local AI models, Aug 3–9, 2026

7 open models released Aug 3–9, 2026, with how each runs on five reference devices.

  1. Qwen3.8 Max (2.4T-A95B)

    Alibaba · LLM · 2,446B (95.0B active) ·

    68Good quality (B) · 68 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  2. Qwen3.8 27B

    Alibaba · LLM · 28B ·

    90Excellent quality (A+) · 90 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  3. Muse Glimmer 30B

    Meta · LLM · 30B ·

    87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, 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. Granite 4.2 30B

    IBM · LLM · 29B ·

    72Great quality (A) · 72 of 100: how capable the model is at Q4_K_M, 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

  5. Maple Preview (20B-A1B)

    DeepGrove · LLM · 20B (1.5B 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

  6. Granite 4.2 8B

    IBM · LLM · 8.8B ·

    68Good quality (B) · 68 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

  7. Granite 4.2 3B

    IBM · LLM · 3.7B ·

    52Fair quality (C) · 52 of 100: how capable the model is at F16, 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

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?