Weekly archive

New local AI models, Jul 7–13, 2025

10 open models released Jul 7–13, 2025, with how each runs on five reference devices.

  1. Kimi K2 Instruct (July 2025)

    Moonshot AI · LLM · 1,026B (32.0B active) ·

    62Good quality (B) · 62 of 100: how capable the model is at Q2_K, 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

  2. CompassJudger-2 32B

    OpenCompass · Decision · 33B ·

    86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  3. FLUX.1 Krea [dev]

    Black Forest Labs · Image · 11.9B ·

    82Great quality (A) · 82 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

  4. CompassJudger-2 7B

    OpenCompass · Decision · 7.6B ·

    77Great quality (A) · 77 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  5. EXAONE 4.0 32B

    LG AI Research · LLM · 32B ·

    68Good quality (B) · 68 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  6. SmolLM3 3B

    Hugging Face · LLM · 3.1B ·

    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. EXAONE 4.0 1.2B

    LG AI Research · LLM · 1.3B ·

    30Basic quality (D) · 30 of 100: how capable the model is at F16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  8. LFM2 1.2B

    Liquid AI · LLM · 1.2B ·

    26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  9. LFM2 700M

    Liquid AI · LLM · 0.7B ·

    18Basic quality (D) · 18 of 100: how capable the model is at F16, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  10. LFM2 350M

    Liquid AI · LLM · 0.4B ·

    12Basic quality (D) · 12 of 100: how capable the model is at F16, whatever it runs on. Match score 47/100 (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?