Weekly archive

New local AI models, Jun 23–29, 2025

8 open models released Jun 23–29, 2025, with how each runs on five reference devices.

  1. Skywork Reward V2 Llama 3.1 8B

    Skywork · Decision · 7.5B ·

    90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  2. Skywork Reward V2 Qwen3 8B

    Skywork · Decision · 7.6B ·

    84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  3. ERNIE 4.5 300B-A47B

    Baidu · LLM · 300B (47.0B active) ·

    76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, 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

  4. Hunyuan A13B (80B-A13B)

    Tencent · LLM · 80B (13.0B active) ·

    73Great quality (A) · 73 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  5. Skywork Reward V2 Qwen3 0.6B

    Skywork · Decision · 600M ·

    72Great quality (A) · 72 of 100: how capable the model is at F16, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  6. ERNIE 4.5 21B-A3B

    Baidu · LLM · 22B (3.0B active) ·

    64Good quality (B) · 64 of 100: how capable the model is at F16, 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. GLM-4.1V 9B Thinking

    Zhipu AI · LLM · 10B ·

    60Good quality (B) · 60 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  8. ERNIE 4.5 0.3B

    Baidu · LLM · 0.4B ·

    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?