Weekly archive

New local AI models, Jun 2–8, 2025

7 open models released Jun 2–8, 2025, with how each runs on five reference devices.

  1. Qwen3 Reranker 4B

    Alibaba · Decision · 4.0B ·

    90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  2. MiniMax-M1 40K

    MiniMax · LLM · 456B (45.9B active) ·

    77Great quality (A) · 77 of 100: how capable the model is at Q4_K_M, 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

  3. Granite Guardian 3.3 8B

    IBM · Decision · 8.2B ·

    80Great quality (A) · 80 of 100: how capable the model is at Q8_0, 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. Magistral Small 2506

    Mistral AI · LLM · 24B ·

    64Good quality (B) · 64 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

  5. OmniGen2

    BAAI (VectorSpaceLab) · Image · 4.0B ·

    66Good quality (B) · 66 of 100: how capable the model is at FP16, 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

  6. MiniCPM4 8B

    OpenBMB · LLM · 8.2B ·

    54Fair quality (C) · 54 of 100: how capable the model is at Q8_0, 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

  7. Gemma 3n E4B

    Google · LLM · 7.9B ·

    46Fair quality (C) · 46 of 100: how capable the model is at F16, whatever it runs on. Match score 63/100 (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?