Weekly archive

New local AI models, Jun 15–21, 2026

10 open models released Jun 15–21, 2026, with how each runs on five reference devices.

  1. GLM-5.2 (753B-A40B)

    Zhipu AI · LLM · 753B (40.0B active) ·

    67Good quality (B) · 67 of 100: how capable the model is at Q2_K, 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

  2. Krea 2 Turbo

    Krea · Image · 12.8B ·

    92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  3. TMax 27B

    Ai2 · LLM · 27B ·

    85Excellent quality (A+) · 85 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  4. Ornith 1.0 35B-A3B

    DeepReinforce · LLM · 36B (3.0B active) ·

    89Excellent quality (A+) · 89 of 100: how capable the model is at F16, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  5. Laguna XS 2.1 (33B-A3B)

    Poolside · LLM · 33B (3.0B active) ·

    82Great quality (A) · 82 of 100: how capable the model is at F16, 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

  6. Ornith 1.0 9B

    DeepReinforce · LLM · 9.7B ·

    75Great quality (A) · 75 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  7. TMax 9B

    Ai2 · LLM · 9.0B ·

    74Great quality (A) · 74 of 100: how capable the model is at Q8_0, 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

  8. TMax 4B

    Ai2 · LLM · 4.2B ·

    61Good quality (B) · 61 of 100: how capable the model is at F16, 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

  9. TMax 2B

    Ai2 · LLM · 1.9B ·

    40Fair quality (C) · 40 of 100: how capable the model is at F16, 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

  10. Unlimited OCR (3B-A0.6B)

    Baidu · LLM · 3.3B (0.6B active) ·

    40Fair quality (C) · 40 of 100: how capable the model is at F16, 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

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?