Weekly archive

New local AI models, Sep 29 – Oct 5, 2025

6 open models released Sep 29 – Oct 5, 2025, with how each runs on five reference devices.

  1. DeepSeek V3.2 Exp

    DeepSeek · LLM · 685B (37.0B active) ·

    77Great quality (A) · 77 of 100: how capable the model is at Q3_K_M, 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

  2. Ling 1T

    Ant Group (inclusionAI) · LLM · 1,000B (50.0B active) ·

    63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  3. GLM-4.6 (355B-A32B)

    Zhipu AI · LLM · 357B (32.0B active) ·

    79Great quality (A) · 79 of 100: how capable the model is at Q4_K_M, 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

  4. Qwen3-VL 30B-A3B Thinking

    Alibaba · LLM · 31B (3.3B active) ·

    76Great quality (A) · 76 of 100: how capable the model is at F16, 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

  5. Qwen3-VL 30B-A3B Instruct

    Alibaba · LLM · 31B (3.3B active) ·

    74Great quality (A) · 74 of 100: how capable the model is at F16, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.

    Runs on

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

  6. Jamba Reasoning 3B

    AI21 Labs · LLM · 3.2B ·

    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?