Weekly archive

New local AI models, Mar 2–8, 2026

7 open models released Mar 2–8, 2026, with how each runs on five reference devices.

  1. FireRed-Image-Edit 1.1

    rednote (FireRed Team) · Image · 20.4B ·

    87Excellent quality (A+) · 87 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

  2. LTX-2.3

    Lightricks · Video · 18.9B ·

    86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, 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

  3. Sarvam 105B

    Sarvam AI · LLM · 106B (10.0B active) ·

    74Great quality (A) · 74 of 100: how capable the model is at Q6_K, 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. Sarvam 30B

    Sarvam AI · LLM · 32B (2.4B active) ·

    70Great quality (A) · 70 of 100: how capable the model is at F16, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  5. Gemma 4 E4B

    Google · LLM · 8.0B ·

    68Good quality (B) · 68 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

  6. Gemma 4 E2B

    Google · LLM · 5.1B ·

    62Good quality (B) · 62 of 100: how capable the model is at F16, 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

  7. Nemotron 3 Nano 4B

    NVIDIA · LLM · 4.0B ·

    50Fair quality (C) · 50 of 100: how capable the model is at F16, whatever it runs on. Match score 64/100 (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?