Weekly archive

New local AI models, Jun 1–7, 2026

6 open models released Jun 1–7, 2026, with how each runs on five reference devices.

  1. Nex N2 Pro (397B-A17B)

    Nex-AGI · LLM · 397B (17.0B active) ·

    92Excellent quality (A+) · 92 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 95/100 (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 M3 (427B)

    MiniMax · LLM · 427B (25.0B active) ·

    90Excellent quality (A+) · 90 of 100: how capable the model is at Q4_K_M, 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

  3. Nemotron 3 Ultra 550B-A55B

    NVIDIA · LLM · 561B (55.0B active) ·

    88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  4. Nex N2 Mini (35B-A3B)

    Nex-AGI · LLM · 35B (3.0B active) ·

    92Excellent quality (A+) · 92 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

  5. Bernini-R A14B (video generation + editing)

    ByteDance · Video · 14.3B ·

    85Excellent quality (A+) · 85 of 100: how capable the model is at FP16, 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

  6. North Mini Code 1.0 (30B-A3B)

    Cohere · LLM · 30B (3.0B active) ·

    80Great quality (A) · 80 of 100: how capable the model is at F16, 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

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?