Weekly archive

New local AI models, Oct 27 – Nov 2, 2025

8 open models released Oct 27 – Nov 2, 2025, with how each runs on five reference devices.

  1. Kimi Linear 48B-A3B

    Moonshot AI · LLM · 49B (3.0B active) ·

    74Great quality (A) · 74 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

  2. Ministral 3 14B Reasoning

    Mistral AI · LLM · 14B ·

    65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  3. Ministral 3 14B

    Mistral AI · LLM · 14B ·

    63Good quality (B) · 63 of 100: how capable the model is at Q6_K, 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

  4. JanusCoder 14B

    Shanghai AI Lab · LLM · 15B ·

    61Good quality (B) · 61 of 100: how capable the model is at Q6_K, 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

  5. Falcon-H1R 7B

    TII · LLM · 7.6B ·

    56Good quality (B) · 56 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  6. Ministral 3 8B

    Mistral AI · LLM · 8.9B ·

    56Good quality (B) · 56 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  7. Fara 7B

    Microsoft · LLM · 8.3B ·

    50Fair quality (C) · 50 of 100: how capable the model is at Q8_0, 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

  8. Ministral 3 3B

    Mistral AI · LLM · 3.9B ·

    44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 62/100 (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?